Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4134 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4737. Min Range: -12.4737
Max Act: 12.4737. Min Act: -0.1700
Data Index: 3518837 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4737. Min Range: -12.4737
Max Act: 12.0987. Min Act: -0.1700
Data Index: 2229491 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.9112. Min Act: -0.1700
Data Index: 2361685 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.9112. Min Act: -0.1700
Data Index: 2196248 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.9112. Min Act: -0.1700
Data Index: 2474742 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.8487. Min Act: -0.1700
Data Index: 2588005 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.8487. Min Act: -0.1700
Data Index: 424633 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.7862. Min Act: -0.1700
Data Index: 8813895 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.6612. Min Act: -0.1700
Data Index: 2792273 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.6612. Min Act: -0.1700
Data Index: 1153734 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.6612. Min Act: -0.1700
Data Index: 4494477 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.6612. Min Act: -0.1700
Data Index: 452920 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.5987. Min Act: -0.1700
Data Index: 1907762 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.5987. Min Act: -0.1700
Data Index: 5636387 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.5362. Min Act: -0.1700
Data Index: 2075149 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.5362. Min Act: -0.1700
Data Index: 8790393 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.5362. Min Act: -0.1700
Data Index: 3118474 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.5362. Min Act: -0.1700
Data Index: 3865022 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.5362. Min Act: -0.1700
Data Index: 5218188 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4737. Min Range: -12.4737
Max Act: 11.5362. Min Act: -0.1700
Data Index: 6682428 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19