Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3829 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.4592. Min Act: -0.1700
Data Index: 6468553 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.4279. Min Act: -0.1700
Data Index: 3241622 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.3965. Min Act: -0.1700
Data Index: 4756348 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.3338. Min Act: -0.1700
Data Index: 3808306 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.3651. Min Act: -0.1700
Data Index: 5908215 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.3338. Min Act: -0.1700
Data Index: 5230904 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.3338. Min Act: -0.1700
Data Index: 5448251 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.3024. Min Act: -0.1700
Data Index: 4623084 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.2867. Min Act: -0.1700
Data Index: 1014055 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.2867. Min Act: -0.1700
Data Index: 1872796 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.2867. Min Act: -0.1700
Data Index: 5012026 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.3024. Min Act: -0.1700
Data Index: 1527450 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.2553. Min Act: -0.1700
Data Index: 3614208 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.3024. Min Act: -0.1700
Data Index: 7859907 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.2867. Min Act: -0.1700
Data Index: 2025971 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.2553. Min Act: -0.1700
Data Index: 8042096 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.2867. Min Act: -0.1700
Data Index: 8408651 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.2710. Min Act: -0.1700
Data Index: 5530990 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.2553. Min Act: -0.1700
Data Index: 4507102 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4592. Min Range: -3.4592
Max Act: 3.2395. Min Act: -0.1700
Data Index: 1120431 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19