Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2190 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1115. Min Range: -7.1115
Max Act: 7.1115. Min Act: -0.1700
Data Index: 8305319 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.8927. Min Act: -0.1700
Data Index: 6076335 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.6427. Min Act: -0.1700
Data Index: 8198471 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.5802. Min Act: -0.1700
Data Index: 8819512 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.5802. Min Act: -0.1700
Data Index: 7070314 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.5490. Min Act: -0.1700
Data Index: 4638650 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.4552. Min Act: -0.1700
Data Index: 3619853 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.4240. Min Act: -0.1700
Data Index: 7415591 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.4240. Min Act: -0.1700
Data Index: 6151916 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.3927. Min Act: -0.1700
Data Index: 3158708 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.3927. Min Act: -0.1700
Data Index: 553121 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.3927. Min Act: -0.1700
Data Index: 929545 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.3927. Min Act: -0.1700
Data Index: 708316 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.3615. Min Act: -0.1700
Data Index: 8240025 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.3615. Min Act: -0.1700
Data Index: 5626603 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.3615. Min Act: -0.1700
Data Index: 4122243 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.3615. Min Act: -0.1700
Data Index: 6649343 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.3302. Min Act: -0.1700
Data Index: 1769889 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.3302. Min Act: -0.1700
Data Index: 8469030 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1115. Min Range: -7.1115
Max Act: 6.2990. Min Act: -0.1700
Data Index: 7461336 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19