Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3862 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.3398. Min Act: -0.1700
Data Index: 1309538 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.3398. Min Act: -0.1700
Data Index: 4246221 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.3085. Min Act: -0.1700
Data Index: 5072651 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.3085. Min Act: -0.1700
Data Index: 6791169 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2773. Min Act: -0.1700
Data Index: 8361788 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2460. Min Act: -0.1700
Data Index: 229321 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2148. Min Act: -0.1700
Data Index: 8135390 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2148. Min Act: -0.1700
Data Index: 355263 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2460. Min Act: -0.1700
Data Index: 7957781 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2148. Min Act: -0.1700
Data Index: 4976600 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2148. Min Act: -0.1700
Data Index: 8666966 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.1835. Min Act: -0.1700
Data Index: 469160 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2148. Min Act: -0.1700
Data Index: 8070398 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.1835. Min Act: -0.1700
Data Index: 8451627 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.1523. Min Act: -0.1700
Data Index: 2488770 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.1366. Min Act: -0.1700
Data Index: 4806827 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.1366. Min Act: -0.1700
Data Index: 3990625 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.1366. Min Act: -0.1700
Data Index: 4962918 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.1366. Min Act: -0.1700
Data Index: 877222 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.1523. Min Act: -0.1700
Data Index: 2353337 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19