Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0408. Min Range: -7.0408
Max Act: 7.0408. Min Act: -0.1700
Data Index: 3802167 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0408. Min Range: -7.0408
Max Act: 7.0408. Min Act: -0.1700
Data Index: 5588157 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.9470. Min Act: -0.1700
Data Index: 2765784 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.9470. Min Act: -0.1700
Data Index: 4484787 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.8533. Min Act: -0.1700
Data Index: 8042966 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.8533. Min Act: -0.1700
Data Index: 3642984 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.8220. Min Act: -0.1700
Data Index: 2067085 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.8220. Min Act: -0.1700
Data Index: 3613280 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.7908. Min Act: -0.1700
Data Index: 6474446 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.7283. Min Act: -0.1700
Data Index: 6582140 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.7283. Min Act: -0.1700
Data Index: 8213513 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.7283. Min Act: -0.1700
Data Index: 1416532 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.6970. Min Act: -0.1700
Data Index: 5394468 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.6970. Min Act: -0.1700
Data Index: 5469239 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.6970. Min Act: -0.1700
Data Index: 8509799 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.6345. Min Act: -0.1700
Data Index: 1701282 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.6658. Min Act: -0.1700
Data Index: 8592831 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.6970. Min Act: -0.1700
Data Index: 4587804 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.6345. Min Act: -0.1700
Data Index: 1064490 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0408. Min Range: -7.0408
Max Act: 6.6033. Min Act: -0.1700
Data Index: 2102428 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19