Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3994 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.8067. Min Act: -0.1700
Data Index: 8286771 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7981. Min Act: -0.1700
Data Index: 3368281 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7723. Min Act: -0.1699
Data Index: 2647155 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7637. Min Act: -0.1700
Data Index: 7931602 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7464. Min Act: -0.1700
Data Index: 6862678 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7464. Min Act: -0.1700
Data Index: 1168109 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7464. Min Act: -0.1700
Data Index: 4936500 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7378. Min Act: -0.1700
Data Index: 3565445 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7291. Min Act: -0.1700
Data Index: 518479 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7205. Min Act: -0.1700
Data Index: 4624635 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7205. Min Act: -0.1700
Data Index: 4046251 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7118. Min Act: -0.1700
Data Index: 1726681 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7118. Min Act: -0.1700
Data Index: 8381936 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7118. Min Act: -0.1700
Data Index: 2647160 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7031. Min Act: -0.1700
Data Index: 5187068 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7031. Min Act: -0.1700
Data Index: 6182630 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7031. Min Act: -0.1700
Data Index: 2995323 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.7031. Min Act: -0.1700
Data Index: 1487289 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.6945. Min Act: -0.1700
Data Index: 5615160 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8067. Min Range: -1.8067
Max Act: 1.6771. Min Act: -0.1700
Data Index: 7684455 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19