Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2602 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1788. Min Range: -9.1788
Max Act: 9.1788. Min Act: -0.1700
Data Index: 8541727 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.9288. Min Act: -0.1700
Data Index: 1887716 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.4288. Min Act: -0.1700
Data Index: 378794 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.2413. Min Act: -0.1700
Data Index: 1987525 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.2413. Min Act: -0.1700
Data Index: 3749537 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.2413. Min Act: -0.1700
Data Index: 6199648 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.2413. Min Act: -0.1700
Data Index: 1960723 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.1788. Min Act: -0.1700
Data Index: 804738 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.2413. Min Act: -0.1700
Data Index: 2109143 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.1788. Min Act: -0.1700
Data Index: 3787629 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.1788. Min Act: -0.1700
Data Index: 8090626 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.1163. Min Act: -0.1700
Data Index: 613323 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.0850. Min Act: -0.1700
Data Index: 4237527 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.0225. Min Act: -0.1700
Data Index: 7794405 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.0850. Min Act: -0.1700
Data Index: 7579545 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.1163. Min Act: -0.1700
Data Index: 5094774 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.0225. Min Act: -0.1700
Data Index: 5047601 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1788. Min Range: -9.1788
Max Act: 8.0225. Min Act: -0.1700
Data Index: 4365174 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1788. Min Range: -9.1788
Max Act: 7.9913. Min Act: -0.1700
Data Index: 1671191 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1788. Min Range: -9.1788
Max Act: 7.9600. Min Act: -0.1700
Data Index: 2713411 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19