Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 648 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2143. Min Range: -4.2143
Max Act: 4.2143. Min Act: -0.1700
Data Index: 3639054 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2143. Min Range: -4.2143
Max Act: 4.2143. Min Act: -0.1700
Data Index: 3615712 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2143. Min Range: -4.2143
Max Act: 4.1206. Min Act: -0.1700
Data Index: 1319412 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2143. Min Range: -4.2143
Max Act: 4.0581. Min Act: -0.1700
Data Index: 5714898 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2143. Min Range: -4.2143
Max Act: 4.0268. Min Act: -0.1700
Data Index: 1735197 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.9955. Min Act: -0.1700
Data Index: 3014691 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.9330. Min Act: -0.1700
Data Index: 3365993 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.9330. Min Act: -0.1700
Data Index: 5633067 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.9330. Min Act: -0.1700
Data Index: 3396554 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.9018. Min Act: -0.1700
Data Index: 4224860 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.9018. Min Act: -0.1700
Data Index: 872652 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.8705. Min Act: -0.1700
Data Index: 6013845 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.9018. Min Act: -0.1700
Data Index: 3854607 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.9018. Min Act: -0.1700
Data Index: 8738580 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.8705. Min Act: -0.1700
Data Index: 905855 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.8705. Min Act: -0.1700
Data Index: 3917762 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.8705. Min Act: -0.1700
Data Index: 607877 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.8705. Min Act: -0.1700
Data Index: 7173206 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.8392. Min Act: -0.1700
Data Index: 147074 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2143. Min Range: -4.2143
Max Act: 3.8392. Min Act: -0.1700
Data Index: 2466153 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19