Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.6879. Min Act: -0.1700
Data Index: 190037 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.6879. Min Act: -0.1700
Data Index: 6552949 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.6566. Min Act: -0.1700
Data Index: 5208014 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.6254. Min Act: -0.1700
Data Index: 3881518 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.6254. Min Act: -0.1700
Data Index: 7945329 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.6254. Min Act: -0.1700
Data Index: 3614095 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.5941. Min Act: -0.1700
Data Index: 5153927 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.5316. Min Act: -0.1700
Data Index: 2680040 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.5004. Min Act: -0.1700
Data Index: 3733026 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.5004. Min Act: -0.1700
Data Index: 1283343 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.5004. Min Act: -0.1700
Data Index: 8261452 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.4691. Min Act: -0.1700
Data Index: 586410 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.4691. Min Act: -0.1700
Data Index: 5832039 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.4379. Min Act: -0.1700
Data Index: 5001576 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.4379. Min Act: -0.1700
Data Index: 3387600 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.4066. Min Act: -0.1700
Data Index: 8297643 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.4066. Min Act: -0.1700
Data Index: 3448274 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.4066. Min Act: -0.1700
Data Index: 2040579 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.4066. Min Act: -0.1700
Data Index: 2303192 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6879. Min Range: -4.6879
Max Act: 4.3754. Min Act: -0.1700
Data Index: 3280246 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19