Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0958. Min Range: -8.0958
Max Act: 8.0958. Min Act: -0.1700
Data Index: 7960633 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0958. Min Range: -8.0958
Max Act: 8.0958. Min Act: -0.1700
Data Index: 8547438 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0958. Min Range: -8.0958
Max Act: 8.0333. Min Act: -0.1700
Data Index: 861216 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0958. Min Range: -8.0958
Max Act: 8.0333. Min Act: -0.1700
Data Index: 1906084 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.9708. Min Act: -0.1700
Data Index: 4164529 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.8458. Min Act: -0.1700
Data Index: 4298791 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.7833. Min Act: -0.1700
Data Index: 2256738 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.7833. Min Act: -0.1700
Data Index: 1547999 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.7208. Min Act: -0.1700
Data Index: 7683056 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.6895. Min Act: -0.1700
Data Index: 3271564 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.6583. Min Act: -0.1700
Data Index: 7743389 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.6583. Min Act: -0.1700
Data Index: 302008 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.6583. Min Act: -0.1700
Data Index: 6666738 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.6270. Min Act: -0.1700
Data Index: 7051504 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.6270. Min Act: -0.1700
Data Index: 2104057 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.6270. Min Act: -0.1700
Data Index: 2177695 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.5958. Min Act: -0.1700
Data Index: 6943932 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.5958. Min Act: -0.1700
Data Index: 4773064 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.5333. Min Act: -0.1700
Data Index: 38566 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0958. Min Range: -8.0958
Max Act: 7.5645. Min Act: -0.1700
Data Index: 4081043 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19