Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3261 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2221. Min Range: -5.2221
Max Act: 5.2221. Min Act: -0.1700
Data Index: 7994642 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2221. Min Range: -5.2221
Max Act: 5.1909. Min Act: -0.1700
Data Index: 915512 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2221. Min Range: -5.2221
Max Act: 5.1284. Min Act: -0.1700
Data Index: 8089951 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2221. Min Range: -5.2221
Max Act: 5.1284. Min Act: -0.1700
Data Index: 8089950 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2221. Min Range: -5.2221
Max Act: 5.0659. Min Act: -0.1700
Data Index: 915511 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.9721. Min Act: -0.1700
Data Index: 5438078 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.9096. Min Act: -0.1700
Data Index: 4233809 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.9096. Min Act: -0.1700
Data Index: 1524876 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.8471. Min Act: -0.1700
Data Index: 915510 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.8784. Min Act: -0.1700
Data Index: 832273 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.8784. Min Act: -0.1700
Data Index: 5073947 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.8784. Min Act: -0.1700
Data Index: 5535769 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.8471. Min Act: -0.1700
Data Index: 7107880 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.8471. Min Act: -0.1700
Data Index: 6418292 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.8471. Min Act: -0.1700
Data Index: 3763204 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.8471. Min Act: -0.1700
Data Index: 1257138 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.8471. Min Act: -0.1700
Data Index: 6794798 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.8159. Min Act: -0.1700
Data Index: 2001836 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.8159. Min Act: -0.1700
Data Index: 6571687 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2221. Min Range: -5.2221
Max Act: 4.7846. Min Act: -0.1700
Data Index: 832274 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19