Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1801 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.8507. Min Act: -0.1700
Data Index: 8206439 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.9132. Min Act: -0.1700
Data Index: 8159906 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.9132. Min Act: -0.1700
Data Index: 8811446 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.8507. Min Act: -0.1700
Data Index: 7314113 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.7882. Min Act: -0.1700
Data Index: 8471061 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.7882. Min Act: -0.1700
Data Index: 6076008 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.7257. Min Act: -0.1700
Data Index: 1767193 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.6632. Min Act: -0.1700
Data Index: 4387666 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.6632. Min Act: -0.1700
Data Index: 7103741 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.6632. Min Act: -0.1700
Data Index: 4553561 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.6632. Min Act: -0.1700
Data Index: 2240242 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.6632. Min Act: -0.1700
Data Index: 6104902 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.6632. Min Act: -0.1700
Data Index: 1250477 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.6007. Min Act: -0.1700
Data Index: 4396618 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.6007. Min Act: -0.1700
Data Index: 5608869 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.6007. Min Act: -0.1700
Data Index: 5830633 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.6632. Min Act: -0.1700
Data Index: 4379499 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.6007. Min Act: -0.1700
Data Index: 5851139 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.5382. Min Act: -0.1700
Data Index: 111818 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9132. Min Range: -7.9132
Max Act: 7.5695. Min Act: -0.1700
Data Index: 4095888 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19