Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2591 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.9667. Min Act: -0.1700
Data Index: 8351339 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.7167. Min Act: -0.1700
Data Index: 2449635 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.6542. Min Act: -0.1700
Data Index: 2398111 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.5917. Min Act: -0.1700
Data Index: 1718570 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.4042. Min Act: -0.1700
Data Index: 5645689 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.2792. Min Act: -0.1700
Data Index: 7609923 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.3417. Min Act: -0.1700
Data Index: 144546 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.4042. Min Act: -0.1700
Data Index: 6353625 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.3417. Min Act: -0.1700
Data Index: 5897956 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.3417. Min Act: -0.1700
Data Index: 5610019 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.3417. Min Act: -0.1700
Data Index: 3964404 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.2792. Min Act: -0.1700
Data Index: 842093 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.2792. Min Act: -0.1700
Data Index: 7986088 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.2167. Min Act: -0.1700
Data Index: 3485604 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.1542. Min Act: -0.1700
Data Index: 4211154 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.1542. Min Act: -0.1700
Data Index: 3837038 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.1542. Min Act: -0.1700
Data Index: 8514937 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.1542. Min Act: -0.1700
Data Index: 6095767 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.0917. Min Act: -0.1700
Data Index: 6031375 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9667. Min Range: -8.9667
Max Act: 8.0917. Min Act: -0.1700
Data Index: 5175504 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19