Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4825 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5855. Min Range: -7.5855
Max Act: 7.5855. Min Act: -0.1700
Data Index: 7616567 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5855. Min Range: -7.5855
Max Act: 7.3355. Min Act: -0.1700
Data Index: 4768312 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5855. Min Range: -7.5855
Max Act: 7.2730. Min Act: -0.1700
Data Index: 3337387 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5855. Min Range: -7.5855
Max Act: 7.2105. Min Act: -0.1700
Data Index: 7684674 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5855. Min Range: -7.5855
Max Act: 7.1792. Min Act: -0.1700
Data Index: 966189 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5855. Min Range: -7.5855
Max Act: 7.0542. Min Act: -0.1700
Data Index: 2178962 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5855. Min Range: -7.5855
Max Act: 7.0542. Min Act: -0.1700
Data Index: 4589988 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5855. Min Range: -7.5855
Max Act: 7.0542. Min Act: -0.1700
Data Index: 1269673 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5855. Min Range: -7.5855
Max Act: 6.9917. Min Act: -0.1700
Data Index: 8657984 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5855. Min Range: -7.5855
Max Act: 6.9917. Min Act: -0.1700
Data Index: 970075 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5855. Min Range: -7.5855
Max Act: 6.8667. Min Act: -0.1700
Data Index: 1535235 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5855. Min Range: -7.5855
Max Act: 6.8980. Min Act: -0.1700
Data Index: 6516831 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5855. Min Range: -7.5855
Max Act: 6.8980. Min Act: -0.1700
Data Index: 5215040 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5855. Min Range: -7.5855
Max Act: 6.8667. Min Act: -0.1700
Data Index: 4558343 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5855. Min Range: -7.5855
Max Act: 6.8667. Min Act: -0.1700
Data Index: 1632684 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5855. Min Range: -7.5855
Max Act: 6.8667. Min Act: -0.1700
Data Index: 2970880 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5855. Min Range: -7.5855
Max Act: 6.8667. Min Act: -0.1700
Data Index: 4427320 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5855. Min Range: -7.5855
Max Act: 6.8667. Min Act: -0.1700
Data Index: 8628488 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5855. Min Range: -7.5855
Max Act: 6.8667. Min Act: -0.1700
Data Index: 627232 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5855. Min Range: -7.5855
Max Act: 6.8042. Min Act: -0.1700
Data Index: 215334 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19