Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 786 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.4055. Min Act: -0.1700
Data Index: 796739 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.2800. Min Act: -0.1700
Data Index: 8140474 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.2486. Min Act: -0.1700
Data Index: 2522394 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.2643. Min Act: -0.1700
Data Index: 5784018 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.2014. Min Act: -0.1700
Data Index: 994781 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.1857. Min Act: -0.1700
Data Index: 2607532 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.1857. Min Act: -0.1700
Data Index: 8402756 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.1699. Min Act: -0.1700
Data Index: 1155203 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.1385. Min Act: -0.1700
Data Index: 2353539 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.1542. Min Act: -0.1700
Data Index: 3315775 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.1227. Min Act: -0.1700
Data Index: 4259066 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.1227. Min Act: -0.1700
Data Index: 5544055 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.1069. Min Act: -0.1700
Data Index: 2353144 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.0912. Min Act: -0.1700
Data Index: 7243657 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.0754. Min Act: -0.1700
Data Index: 3299402 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.0912. Min Act: -0.1700
Data Index: 7780486 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.0912. Min Act: -0.1700
Data Index: 131533 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.0596. Min Act: -0.1700
Data Index: 2699296 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.0596. Min Act: -0.1700
Data Index: 6177845 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4055. Min Range: -3.4055
Max Act: 3.0754. Min Act: -0.1700
Data Index: 486660 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19