Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1005 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.9408. Min Act: -0.1700
Data Index: 5730474 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.8783. Min Act: -0.1700
Data Index: 3048971 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.8470. Min Act: -0.1700
Data Index: 3492366 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.8470. Min Act: -0.1700
Data Index: 8023436 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.8470. Min Act: -0.1700
Data Index: 77563 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.8158. Min Act: -0.1700
Data Index: 548327 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.7533. Min Act: -0.1700
Data Index: 6949699 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.7533. Min Act: -0.1700
Data Index: 8601063 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.7533. Min Act: -0.1700
Data Index: 82207 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.7845. Min Act: -0.1700
Data Index: 2726616 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.7220. Min Act: -0.1700
Data Index: 2140969 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.7533. Min Act: -0.1700
Data Index: 2100850 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.7220. Min Act: -0.1700
Data Index: 4934112 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.6908. Min Act: -0.1700
Data Index: 3368917 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.7220. Min Act: -0.1700
Data Index: 6751095 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.7220. Min Act: -0.1700
Data Index: 5976120 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.6908. Min Act: -0.1700
Data Index: 2664844 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.6908. Min Act: -0.1700
Data Index: 1442563 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.6908. Min Act: -0.1700
Data Index: 6540121 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9408. Min Range: -5.9408
Max Act: 5.6908. Min Act: -0.1700
Data Index: 398022 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19