Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3237 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5902. Min Range: -8.5902
Max Act: 8.5902. Min Act: -0.1700
Data Index: 2211086 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5902. Min Range: -8.5902
Max Act: 8.3402. Min Act: -0.1700
Data Index: 5207509 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5902. Min Range: -8.5902
Max Act: 8.2777. Min Act: -0.1700
Data Index: 1599720 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5902. Min Range: -8.5902
Max Act: 8.2152. Min Act: -0.1700
Data Index: 7877964 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5902. Min Range: -8.5902
Max Act: 8.1527. Min Act: -0.1700
Data Index: 3567394 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5902. Min Range: -8.5902
Max Act: 8.0277. Min Act: -0.1700
Data Index: 3231397 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5902. Min Range: -8.5902
Max Act: 8.0277. Min Act: -0.1700
Data Index: 5138358 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5902. Min Range: -8.5902
Max Act: 8.0277. Min Act: -0.1700
Data Index: 8721103 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5902. Min Range: -8.5902
Max Act: 7.9652. Min Act: -0.1700
Data Index: 8726991 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5902. Min Range: -8.5902
Max Act: 7.9652. Min Act: -0.1700
Data Index: 2759815 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5902. Min Range: -8.5902
Max Act: 8.0277. Min Act: -0.1700
Data Index: 6602780 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5902. Min Range: -8.5902
Max Act: 7.9652. Min Act: -0.1700
Data Index: 8079362 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5902. Min Range: -8.5902
Max Act: 7.9027. Min Act: -0.1700
Data Index: 7017555 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5902. Min Range: -8.5902
Max Act: 7.9027. Min Act: -0.1700
Data Index: 2449535 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5902. Min Range: -8.5902
Max Act: 7.9027. Min Act: -0.1700
Data Index: 7923154 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5902. Min Range: -8.5902
Max Act: 7.8402. Min Act: -0.1700
Data Index: 1819314 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5902. Min Range: -8.5902
Max Act: 7.9027. Min Act: -0.1700
Data Index: 4918681 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5902. Min Range: -8.5902
Max Act: 7.9027. Min Act: -0.1700
Data Index: 2875358 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5902. Min Range: -8.5902
Max Act: 7.8402. Min Act: -0.1700
Data Index: 2342682 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5902. Min Range: -8.5902
Max Act: 7.8402. Min Act: -0.1700
Data Index: 1779248 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19