Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 432 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.6542. Min Act: -0.1700
Data Index: 3492175 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.6629. Min Act: -0.1700
Data Index: 5079960 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.6455. Min Act: -0.1700
Data Index: 5751023 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.6368. Min Act: -0.1700
Data Index: 1225146 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.6194. Min Act: -0.1700
Data Index: 1039746 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.6019. Min Act: -0.1700
Data Index: 3998310 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.5932. Min Act: -0.1700
Data Index: 2091245 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.5582. Min Act: -0.1700
Data Index: 5302750 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.5670. Min Act: -0.1700
Data Index: 8210863 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.5670. Min Act: -0.1700
Data Index: 2641579 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.5582. Min Act: -0.1700
Data Index: 3697090 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.5582. Min Act: -0.1700
Data Index: 7888428 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.5495. Min Act: -0.1700
Data Index: 3947012 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.5495. Min Act: -0.1700
Data Index: 7011866 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.5495. Min Act: -0.1700
Data Index: 2149600 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.5319. Min Act: -0.1700
Data Index: 3125152 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.5407. Min Act: -0.1700
Data Index: 5380248 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.5407. Min Act: -0.1700
Data Index: 4529601 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.5495. Min Act: -0.1700
Data Index: 7768918 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6629. Min Range: -1.6629
Max Act: 1.5319. Min Act: -0.1700
Data Index: 3177222 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19