Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 862 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5135. Min Range: -7.5135
Max Act: 7.5135. Min Act: -0.1700
Data Index: 2783443 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5135. Min Range: -7.5135
Max Act: 7.4510. Min Act: -0.1700
Data Index: 51481 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5135. Min Range: -7.5135
Max Act: 7.2322. Min Act: -0.1700
Data Index: 3688158 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5135. Min Range: -7.5135
Max Act: 7.0760. Min Act: -0.1700
Data Index: 2074657 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5135. Min Range: -7.5135
Max Act: 7.0447. Min Act: -0.1700
Data Index: 2886318 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.9822. Min Act: -0.1700
Data Index: 8638304 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.9822. Min Act: -0.1700
Data Index: 5268829 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.9510. Min Act: -0.1700
Data Index: 1707253 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.9510. Min Act: -0.1700
Data Index: 23072 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.9197. Min Act: -0.1700
Data Index: 2371565 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.8885. Min Act: -0.1700
Data Index: 6184013 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.9197. Min Act: -0.1700
Data Index: 6343216 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.8572. Min Act: -0.1700
Data Index: 4163314 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.8572. Min Act: -0.1700
Data Index: 5261204 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.8885. Min Act: -0.1700
Data Index: 6169956 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.8260. Min Act: -0.1700
Data Index: 7694160 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.8260. Min Act: -0.1700
Data Index: 1667597 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.8260. Min Act: -0.1700
Data Index: 869622 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.7947. Min Act: -0.1700
Data Index: 783643 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5135. Min Range: -7.5135
Max Act: 6.7947. Min Act: -0.1700
Data Index: 1438327 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19