Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2778 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1742. Min Range: -7.1742
Max Act: 7.1742. Min Act: -0.1700
Data Index: 2810812 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1742. Min Range: -7.1742
Max Act: 7.1742. Min Act: -0.1700
Data Index: 2994758 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1742. Min Range: -7.1742
Max Act: 7.0805. Min Act: -0.1700
Data Index: 2994761 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1742. Min Range: -7.1742
Max Act: 7.0805. Min Act: -0.1700
Data Index: 5528637 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1742. Min Range: -7.1742
Max Act: 7.0492. Min Act: -0.1700
Data Index: 2743016 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1742. Min Range: -7.1742
Max Act: 7.0180. Min Act: -0.1700
Data Index: 4991937 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1742. Min Range: -7.1742
Max Act: 6.9555. Min Act: -0.1700
Data Index: 5725246 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1742. Min Range: -7.1742
Max Act: 6.9555. Min Act: -0.1700
Data Index: 6954809 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1742. Min Range: -7.1742
Max Act: 6.8930. Min Act: -0.1700
Data Index: 4325266 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1742. Min Range: -7.1742
Max Act: 6.8617. Min Act: -0.1700
Data Index: 7319630 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1742. Min Range: -7.1742
Max Act: 6.8617. Min Act: -0.1700
Data Index: 2917463 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1742. Min Range: -7.1742
Max Act: 6.8305. Min Act: -0.1700
Data Index: 790945 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1742. Min Range: -7.1742
Max Act: 6.7992. Min Act: -0.1700
Data Index: 5880594 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1742. Min Range: -7.1742
Max Act: 6.7992. Min Act: -0.1700
Data Index: 967325 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1742. Min Range: -7.1742
Max Act: 6.8305. Min Act: -0.1700
Data Index: 485240 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1742. Min Range: -7.1742
Max Act: 6.7992. Min Act: -0.1700
Data Index: 708853 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1742. Min Range: -7.1742
Max Act: 6.8305. Min Act: -0.1700
Data Index: 1378082 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1742. Min Range: -7.1742
Max Act: 6.7680. Min Act: -0.1700
Data Index: 2326199 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1742. Min Range: -7.1742
Max Act: 6.7680. Min Act: -0.1700
Data Index: 4414217 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1742. Min Range: -7.1742
Max Act: 6.7367. Min Act: -0.1700
Data Index: 3306118 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19