Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 535 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0297. Min Range: -7.0297
Max Act: 7.0297. Min Act: -0.1700
Data Index: 8201583 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.9047. Min Act: -0.1700
Data Index: 2370792 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.9047. Min Act: -0.1700
Data Index: 2771052 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.8109. Min Act: -0.1700
Data Index: 1003209 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.7797. Min Act: -0.1700
Data Index: 1195233 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.7797. Min Act: -0.1700
Data Index: 8751235 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.7484. Min Act: -0.1700
Data Index: 3217127 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.7484. Min Act: -0.1700
Data Index: 6646752 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.6547. Min Act: -0.1700
Data Index: 6367839 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.5922. Min Act: -0.1700
Data Index: 4709087 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.4984. Min Act: -0.1700
Data Index: 2445762 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.4672. Min Act: -0.1700
Data Index: 1095550 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.4672. Min Act: -0.1700
Data Index: 2405990 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.4047. Min Act: -0.1700
Data Index: 6017610 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.4047. Min Act: -0.1700
Data Index: 1399537 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.4047. Min Act: -0.1700
Data Index: 6218197 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.4047. Min Act: -0.1700
Data Index: 1592401 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.4047. Min Act: -0.1700
Data Index: 4693525 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.4047. Min Act: -0.1700
Data Index: 4028529 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0297. Min Range: -7.0297
Max Act: 6.3734. Min Act: -0.1700
Data Index: 5704288 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19