Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 582 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.7432. Min Range: -9.7432
Max Act: 9.7432. Min Act: -0.1700
Data Index: 2408889 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7432. Min Range: -9.7432
Max Act: 9.7432. Min Act: -0.1700
Data Index: 1653244 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7432. Min Range: -9.7432
Max Act: 9.5557. Min Act: -0.1700
Data Index: 3572687 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7432. Min Range: -9.7432
Max Act: 9.5557. Min Act: -0.1700
Data Index: 4456514 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7432. Min Range: -9.7432
Max Act: 9.4932. Min Act: -0.1700
Data Index: 2590258 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7432. Min Range: -9.7432
Max Act: 9.4307. Min Act: -0.1700
Data Index: 6678219 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7432. Min Range: -9.7432
Max Act: 9.1807. Min Act: -0.1700
Data Index: 5543128 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7432. Min Range: -9.7432
Max Act: 9.1182. Min Act: -0.1700
Data Index: 8051684 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7432. Min Range: -9.7432
Max Act: 9.0557. Min Act: -0.1700
Data Index: 2376176 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7432. Min Range: -9.7432
Max Act: 9.1182. Min Act: -0.1700
Data Index: 628876 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7432. Min Range: -9.7432
Max Act: 9.0557. Min Act: -0.1700
Data Index: 2085061 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7432. Min Range: -9.7432
Max Act: 8.9932. Min Act: -0.1700
Data Index: 4829157 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7432. Min Range: -9.7432
Max Act: 8.9307. Min Act: -0.1700
Data Index: 547362 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7432. Min Range: -9.7432
Max Act: 8.8682. Min Act: -0.1700
Data Index: 8212156 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7432. Min Range: -9.7432
Max Act: 8.8057. Min Act: -0.1700
Data Index: 1525882 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7432. Min Range: -9.7432
Max Act: 8.8057. Min Act: -0.1700
Data Index: 6870851 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7432. Min Range: -9.7432
Max Act: 8.7432. Min Act: -0.1700
Data Index: 805116 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7432. Min Range: -9.7432
Max Act: 8.7432. Min Act: -0.1700
Data Index: 5783573 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7432. Min Range: -9.7432
Max Act: 8.6807. Min Act: -0.1700
Data Index: 4422398 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7432. Min Range: -9.7432
Max Act: 8.6182. Min Act: -0.1700
Data Index: 5863223 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19