Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4329 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5247. Min Range: -8.5247
Max Act: 8.5247. Min Act: -0.1700
Data Index: 7397215 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.8060. Min Act: -0.1700
Data Index: 4079304 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.8060. Min Act: -0.1700
Data Index: 1195677 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.8372. Min Act: -0.1700
Data Index: 347861 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.7747. Min Act: -0.1700
Data Index: 7690757 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.7435. Min Act: -0.1700
Data Index: 3920338 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.7435. Min Act: -0.1700
Data Index: 106367 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.6185. Min Act: -0.1700
Data Index: 5429730 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.5872. Min Act: -0.1700
Data Index: 3424631 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.5872. Min Act: -0.1700
Data Index: 3707146 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.5560. Min Act: -0.1700
Data Index: 5948639 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.5247. Min Act: -0.1700
Data Index: 6507173 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.5247. Min Act: -0.1700
Data Index: 7912692 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.5247. Min Act: -0.1700
Data Index: 4112621 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.4622. Min Act: -0.1700
Data Index: 2708137 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.4622. Min Act: -0.1700
Data Index: 976641 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.4935. Min Act: -0.1700
Data Index: 1443368 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.4622. Min Act: -0.1700
Data Index: 4548357 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.4622. Min Act: -0.1700
Data Index: 50911 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5247. Min Range: -8.5247
Max Act: 7.4310. Min Act: -0.1700
Data Index: 7148336 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19