Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3436 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.6154. Min Act: -0.1700
Data Index: 1420049 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.4904. Min Act: -0.1700
Data Index: 8412712 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.4592. Min Act: -0.1700
Data Index: 5495129 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.3967. Min Act: -0.1700
Data Index: 7540964 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.3654. Min Act: -0.1700
Data Index: 7572849 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.3342. Min Act: -0.1700
Data Index: 5960683 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.3654. Min Act: -0.1700
Data Index: 2983370 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.3654. Min Act: -0.1700
Data Index: 7584593 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.3342. Min Act: -0.1700
Data Index: 3910219 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.3342. Min Act: -0.1700
Data Index: 5900448 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.3654. Min Act: -0.1700
Data Index: 7254274 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.3029. Min Act: -0.1700
Data Index: 6314663 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.2717. Min Act: -0.1700
Data Index: 2188536 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.2717. Min Act: -0.1700
Data Index: 2062915 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.2717. Min Act: -0.1700
Data Index: 2844643 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.2404. Min Act: -0.1700
Data Index: 7613461 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.2404. Min Act: -0.1700
Data Index: 7303148 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.2404. Min Act: -0.1700
Data Index: 2984929 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.2404. Min Act: -0.1700
Data Index: 4447030 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6154. Min Range: -4.6154
Max Act: 4.2717. Min Act: -0.1700
Data Index: 1923256 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19