Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1253 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6430. Min Act: -0.1700
Data Index: 249929 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6911. Min Act: -0.1700
Data Index: 4556929 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5787. Min Act: -0.1700
Data Index: 1747463 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5787. Min Act: -0.1700
Data Index: 3566738 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5787. Min Act: -0.1700
Data Index: 6367499 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5626. Min Act: -0.1700
Data Index: 5488183 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5787. Min Act: -0.1700
Data Index: 6511609 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5626. Min Act: -0.1700
Data Index: 5698738 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5464. Min Act: -0.1700
Data Index: 1630857 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5464. Min Act: -0.1700
Data Index: 1967427 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5464. Min Act: -0.1700
Data Index: 792037 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5464. Min Act: -0.1700
Data Index: 2228430 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5464. Min Act: -0.1700
Data Index: 3566737 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5626. Min Act: -0.1700
Data Index: 1042860 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5141. Min Act: -0.1700
Data Index: 4088064 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5303. Min Act: -0.1700
Data Index: 362877 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5141. Min Act: -0.1700
Data Index: 6722157 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.4979. Min Act: -0.1700
Data Index: 4209560 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.5303. Min Act: -0.1700
Data Index: 7151205 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.4817. Min Act: -0.1700
Data Index: 8235357 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19