Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6349 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.5740. Min Act: -0.1700
Data Index: 4275972 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.5565. Min Act: -0.1700
Data Index: 7008673 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.5565. Min Act: -0.1700
Data Index: 1886156 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.5389. Min Act: -0.1656
Data Index: 945174 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.5214. Min Act: -0.1700
Data Index: 6366214 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.5214. Min Act: -0.1700
Data Index: 8411655 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.5039. Min Act: -0.1694
Data Index: 7008672 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.4863. Min Act: -0.1680
Data Index: 2621026 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.5039. Min Act: -0.1700
Data Index: 5177668 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.4863. Min Act: -0.1683
Data Index: 5027897 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.4687. Min Act: -0.1696
Data Index: 6970564 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.4863. Min Act: -0.1698
Data Index: 3756820 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.4863. Min Act: -0.1700
Data Index: 3824022 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.4511. Min Act: -0.1700
Data Index: 6640745 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.4511. Min Act: -0.1700
Data Index: 6407988 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.4511. Min Act: -0.1700
Data Index: 5305949 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.4687. Min Act: -0.1698
Data Index: 3450968 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.4511. Min Act: -0.1694
Data Index: 2488944 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.4511. Min Act: -0.1688
Data Index: 823000 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5740. Min Range: -1.5740
Max Act: 1.4511. Min Act: -0.1699
Data Index: 4871222 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19