Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2329 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2280. Min Range: -6.2280
Max Act: 6.2280. Min Act: -0.1700
Data Index: 6105180 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.8842. Min Act: -0.1700
Data Index: 8138989 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.8217. Min Act: -0.1700
Data Index: 5387725 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.7280. Min Act: -0.1700
Data Index: 413985 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.7280. Min Act: -0.1700
Data Index: 97940 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.6967. Min Act: -0.1700
Data Index: 7886358 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.6655. Min Act: -0.1700
Data Index: 1264584 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.5717. Min Act: -0.1700
Data Index: 1348805 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.6030. Min Act: -0.1700
Data Index: 5991920 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.5717. Min Act: -0.1700
Data Index: 7354343 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.5717. Min Act: -0.1700
Data Index: 7575741 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.5405. Min Act: -0.1700
Data Index: 5645537 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.5405. Min Act: -0.1700
Data Index: 8645079 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.5405. Min Act: -0.1700
Data Index: 3369582 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.4780. Min Act: -0.1700
Data Index: 2523173 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.4780. Min Act: -0.1700
Data Index: 22924 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.4780. Min Act: -0.1700
Data Index: 3683642 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.4467. Min Act: -0.1700
Data Index: 1052362 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.4780. Min Act: -0.1700
Data Index: 7456040 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2280. Min Range: -6.2280
Max Act: 5.4155. Min Act: -0.1700
Data Index: 3547775 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19