Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3835 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.4490. Min Act: -0.1700
Data Index: 2845378 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.4333. Min Act: -0.1700
Data Index: 3636966 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.3236. Min Act: -0.1700
Data Index: 2620483 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.3549. Min Act: -0.1700
Data Index: 434621 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.2922. Min Act: -0.1700
Data Index: 4123938 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.3079. Min Act: -0.1700
Data Index: 921305 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.2451. Min Act: -0.1700
Data Index: 8525567 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.2608. Min Act: -0.1700
Data Index: 7775726 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.2451. Min Act: -0.1700
Data Index: 4955246 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.1664. Min Act: -0.1700
Data Index: 8628895 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.1822. Min Act: -0.1700
Data Index: 819452 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.1664. Min Act: -0.1700
Data Index: 5884721 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.1192. Min Act: -0.1700
Data Index: 792676 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.1507. Min Act: -0.1700
Data Index: 4189057 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.1349. Min Act: -0.1700
Data Index: 1634367 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.1034. Min Act: -0.1700
Data Index: 4347805 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.0877. Min Act: -0.1700
Data Index: 7723686 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.1034. Min Act: -0.1700
Data Index: 6115772 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.0719. Min Act: -0.1700
Data Index: 1379812 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4490. Min Range: -3.4490
Max Act: 3.0877. Min Act: -0.1700
Data Index: 1752669 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19