Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5905 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.6356. Min Act: -0.1700
Data Index: 6083135 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.5731. Min Act: -0.1700
Data Index: 6621445 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.4481. Min Act: -0.1700
Data Index: 1881501 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.4169. Min Act: -0.1700
Data Index: 8511156 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.2919. Min Act: -0.1700
Data Index: 2464938 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.2919. Min Act: -0.1700
Data Index: 6624590 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.1981. Min Act: -0.1700
Data Index: 437062 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.1669. Min Act: -0.1700
Data Index: 2988108 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.1356. Min Act: -0.1700
Data Index: 8655202 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.1356. Min Act: -0.1700
Data Index: 3054969 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.0731. Min Act: -0.1700
Data Index: 791430 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.0731. Min Act: -0.1700
Data Index: 8790878 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.0731. Min Act: -0.1700
Data Index: 5338650 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.0731. Min Act: -0.1700
Data Index: 3513696 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.0731. Min Act: -0.1700
Data Index: 4123640 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.0419. Min Act: -0.1700
Data Index: 1364030 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.0106. Min Act: -0.1700
Data Index: 395672 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.0106. Min Act: -0.1700
Data Index: 3271886 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.0106. Min Act: -0.1700
Data Index: 4951935 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6356. Min Range: -7.6356
Max Act: 7.0106. Min Act: -0.1700
Data Index: 3314300 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19