Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 653 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.7939. Min Act: -0.1700
Data Index: 5451428 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.7939. Min Act: -0.1700
Data Index: 2259593 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.6064. Min Act: -0.1700
Data Index: 5853651 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.6064. Min Act: -0.1700
Data Index: 8368853 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.5751. Min Act: -0.1700
Data Index: 1223596 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.3251. Min Act: -0.1700
Data Index: 3908061 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.3564. Min Act: -0.1700
Data Index: 1589743 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.2939. Min Act: -0.1700
Data Index: 3727308 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.2314. Min Act: -0.1700
Data Index: 165713 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.2314. Min Act: -0.1700
Data Index: 6796890 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.1689. Min Act: -0.1700
Data Index: 3590789 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.2001. Min Act: -0.1700
Data Index: 8495843 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.1689. Min Act: -0.1700
Data Index: 2355729 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.1064. Min Act: -0.1700
Data Index: 3181437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.1064. Min Act: -0.1700
Data Index: 6580451 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.1064. Min Act: -0.1700
Data Index: 7560568 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.1064. Min Act: -0.1700
Data Index: 3928654 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.0751. Min Act: -0.1700
Data Index: 6594616 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.0751. Min Act: -0.1700
Data Index: 3590240 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7939. Min Range: -7.7939
Max Act: 7.0439. Min Act: -0.1700
Data Index: 2725433 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19