Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4121 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6509. Min Range: -10.6509
Max Act: 10.6509. Min Act: -0.1700
Data Index: 5233895 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6509. Min Range: -10.6509
Max Act: 10.3384. Min Act: -0.1700
Data Index: 1254189 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6509. Min Range: -10.6509
Max Act: 10.3384. Min Act: -0.1700
Data Index: 672075 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6509. Min Range: -10.6509
Max Act: 10.2759. Min Act: -0.1700
Data Index: 7391018 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6509. Min Range: -10.6509
Max Act: 10.2134. Min Act: -0.1699
Data Index: 5274276 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6509. Min Range: -10.6509
Max Act: 10.0259. Min Act: -0.1700
Data Index: 7247452 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6509. Min Range: -10.6509
Max Act: 10.0884. Min Act: -0.1700
Data Index: 3322360 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6509. Min Range: -10.6509
Max Act: 9.9009. Min Act: -0.1700
Data Index: 8359273 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6509. Min Range: -10.6509
Max Act: 9.9634. Min Act: -0.1700
Data Index: 2680873 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6509. Min Range: -10.6509
Max Act: 9.9634. Min Act: -0.1700
Data Index: 2326 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6509. Min Range: -10.6509
Max Act: 9.9009. Min Act: -0.1700
Data Index: 4182423 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6509. Min Range: -10.6509
Max Act: 9.9009. Min Act: -0.1700
Data Index: 571123 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6509. Min Range: -10.6509
Max Act: 9.9009. Min Act: -0.1700
Data Index: 8506095 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6509. Min Range: -10.6509
Max Act: 9.8384. Min Act: -0.1700
Data Index: 4684153 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6509. Min Range: -10.6509
Max Act: 9.9009. Min Act: -0.1700
Data Index: 6378353 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6509. Min Range: -10.6509
Max Act: 9.7759. Min Act: -0.1700
Data Index: 824825 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6509. Min Range: -10.6509
Max Act: 9.8384. Min Act: -0.1700
Data Index: 3818696 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6509. Min Range: -10.6509
Max Act: 9.7759. Min Act: -0.1700
Data Index: 6777449 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6509. Min Range: -10.6509
Max Act: 9.6509. Min Act: -0.1700
Data Index: 2611485 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6509. Min Range: -10.6509
Max Act: 9.7134. Min Act: -0.1700
Data Index: 3144104 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19