Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2981 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.4391. Min Act: -0.1700
Data Index: 2407189 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.4077. Min Act: -0.1700
Data Index: 1243151 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.4077. Min Act: -0.1700
Data Index: 1062340 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.2979. Min Act: -0.1700
Data Index: 1387527 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.2979. Min Act: -0.1700
Data Index: 4995157 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.2665. Min Act: -0.1700
Data Index: 253524 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.2665. Min Act: -0.1700
Data Index: 2867815 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.2194. Min Act: -0.1700
Data Index: 5031853 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.2351. Min Act: -0.1700
Data Index: 6071154 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.2037. Min Act: -0.1700
Data Index: 3101937 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.1879. Min Act: -0.1700
Data Index: 5963758 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.1879. Min Act: -0.1700
Data Index: 154236 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.2037. Min Act: -0.1700
Data Index: 7783249 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.1565. Min Act: -0.1700
Data Index: 3314391 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.1565. Min Act: -0.1700
Data Index: 4076720 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.1722. Min Act: -0.1700
Data Index: 5604160 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.1407. Min Act: -0.1700
Data Index: 4869482 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.1092. Min Act: -0.1700
Data Index: 2393218 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.1250. Min Act: -0.1700
Data Index: 5681220 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4391. Min Range: -3.4391
Max Act: 3.1250. Min Act: -0.1700
Data Index: 5416634 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19