Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7049. Min Range: -7.7049
Max Act: 7.7049. Min Act: -0.1700
Data Index: 1565061 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7049. Min Range: -7.7049
Max Act: 7.3612. Min Act: -0.1700
Data Index: 5872231 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7049. Min Range: -7.7049
Max Act: 7.2674. Min Act: -0.1700
Data Index: 7969221 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7049. Min Range: -7.7049
Max Act: 7.1737. Min Act: -0.1700
Data Index: 7679346 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7049. Min Range: -7.7049
Max Act: 7.1737. Min Act: -0.1700
Data Index: 2459161 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7049. Min Range: -7.7049
Max Act: 7.1424. Min Act: -0.1700
Data Index: 8128928 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7049. Min Range: -7.7049
Max Act: 7.1424. Min Act: -0.1700
Data Index: 8128942 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7049. Min Range: -7.7049
Max Act: 7.1112. Min Act: -0.1700
Data Index: 783409 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7049. Min Range: -7.7049
Max Act: 7.1112. Min Act: -0.1700
Data Index: 3251063 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7049. Min Range: -7.7049
Max Act: 7.0487. Min Act: -0.1700
Data Index: 1568050 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7049. Min Range: -7.7049
Max Act: 7.0174. Min Act: -0.1700
Data Index: 7939924 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7049. Min Range: -7.7049
Max Act: 7.0487. Min Act: -0.1700
Data Index: 8816134 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7049. Min Range: -7.7049
Max Act: 7.0174. Min Act: -0.1700
Data Index: 1563288 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7049. Min Range: -7.7049
Max Act: 6.9862. Min Act: -0.1700
Data Index: 7184587 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7049. Min Range: -7.7049
Max Act: 6.9549. Min Act: -0.1700
Data Index: 3283646 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7049. Min Range: -7.7049
Max Act: 6.9549. Min Act: -0.1700
Data Index: 4464365 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7049. Min Range: -7.7049
Max Act: 6.9549. Min Act: -0.1700
Data Index: 8741985 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7049. Min Range: -7.7049
Max Act: 6.9549. Min Act: -0.1700
Data Index: 6129359 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7049. Min Range: -7.7049
Max Act: 6.9237. Min Act: -0.1700
Data Index: 7263175 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7049. Min Range: -7.7049
Max Act: 6.9237. Min Act: -0.1700
Data Index: 2542129 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19