Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2053 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.8921. Min Act: -0.1700
Data Index: 3808246 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.5171. Min Act: -0.1700
Data Index: 5312441 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.4859. Min Act: -0.1700
Data Index: 2165460 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.3609. Min Act: -0.1700
Data Index: 2870996 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.3609. Min Act: -0.1700
Data Index: 6444545 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.3296. Min Act: -0.1700
Data Index: 8222004 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.3296. Min Act: -0.1700
Data Index: 3652966 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.2671. Min Act: -0.1700
Data Index: 8469412 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.2984. Min Act: -0.1700
Data Index: 4354562 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.2671. Min Act: -0.1700
Data Index: 6583309 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.2671. Min Act: -0.1700
Data Index: 7236300 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.2359. Min Act: -0.1700
Data Index: 6480702 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.2359. Min Act: -0.1700
Data Index: 8427428 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.2359. Min Act: -0.1700
Data Index: 7674400 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.2359. Min Act: -0.1700
Data Index: 2719042 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.2046. Min Act: -0.1700
Data Index: 2065704 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.2046. Min Act: -0.1700
Data Index: 1662631 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.2046. Min Act: -0.1700
Data Index: 7355023 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.2046. Min Act: -0.1700
Data Index: 5780042 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8921. Min Range: -6.8921
Max Act: 6.1734. Min Act: -0.1700
Data Index: 321297 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19