Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1455 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.5763. Min Act: -0.1700
Data Index: 8753880 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.4513. Min Act: -0.1700
Data Index: 1710321 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.4826. Min Act: -0.1700
Data Index: 2755329 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.4513. Min Act: -0.1700
Data Index: 2747652 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.4201. Min Act: -0.1700
Data Index: 4036540 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.3888. Min Act: -0.1700
Data Index: 6772091 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.3888. Min Act: -0.1700
Data Index: 4793579 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.3263. Min Act: -0.1700
Data Index: 2591607 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.3575. Min Act: -0.1700
Data Index: 8155133 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.3263. Min Act: -0.1700
Data Index: 7669795 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.3575. Min Act: -0.1700
Data Index: 780894 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.2950. Min Act: -0.1700
Data Index: 7506906 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.2950. Min Act: -0.1700
Data Index: 5718761 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.2950. Min Act: -0.1700
Data Index: 2257779 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.3263. Min Act: -0.1700
Data Index: 1089960 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.2950. Min Act: -0.1700
Data Index: 6409864 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.2638. Min Act: -0.1700
Data Index: 6650834 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.2638. Min Act: -0.1700
Data Index: 131086 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.2950. Min Act: -0.1700
Data Index: 3405910 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5763. Min Range: -4.5763
Max Act: 4.2950. Min Act: -0.1700
Data Index: 6046938 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19