Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3146 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1032. Min Range: -7.1032
Max Act: 7.1032. Min Act: -0.1700
Data Index: 40968 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.7594. Min Act: -0.1700
Data Index: 8167454 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.7282. Min Act: -0.1700
Data Index: 2672298 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.6969. Min Act: -0.1700
Data Index: 3913701 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.6344. Min Act: -0.1700
Data Index: 4016713 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.4782. Min Act: -0.1700
Data Index: 7558218 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.4469. Min Act: -0.1700
Data Index: 1543049 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.4157. Min Act: -0.1700
Data Index: 8121803 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.3219. Min Act: -0.1700
Data Index: 2672519 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.2907. Min Act: -0.1700
Data Index: 2779701 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.3219. Min Act: -0.1700
Data Index: 5832242 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.2594. Min Act: -0.1700
Data Index: 2449962 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.2282. Min Act: -0.1700
Data Index: 4775110 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.1969. Min Act: -0.1700
Data Index: 6791193 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.1657. Min Act: -0.1700
Data Index: 2301616 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.1969. Min Act: -0.1700
Data Index: 1954516 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.1969. Min Act: -0.1700
Data Index: 5827094 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.1657. Min Act: -0.1700
Data Index: 8498818 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.1657. Min Act: -0.1700
Data Index: 1936664 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1032. Min Range: -7.1032
Max Act: 6.1344. Min Act: -0.1700
Data Index: 5572146 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19