Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 621 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.5294. Min Act: -0.1700
Data Index: 2357426 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.4356. Min Act: -0.1700
Data Index: 5644433 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.4356. Min Act: -0.1700
Data Index: 5350656 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.3731. Min Act: -0.1700
Data Index: 1641706 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.3106. Min Act: -0.1699
Data Index: 8772039 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.3106. Min Act: -0.1699
Data Index: 6780412 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.3106. Min Act: -0.1700
Data Index: 2905117 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.3106. Min Act: -0.1699
Data Index: 3892533 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.2794. Min Act: -0.1700
Data Index: 1833129 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.2794. Min Act: -0.1700
Data Index: 1132800 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.2481. Min Act: -0.1700
Data Index: 7064578 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.2169. Min Act: -0.1700
Data Index: 2204029 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.2481. Min Act: -0.1700
Data Index: 6909193 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.2169. Min Act: -0.1700
Data Index: 3807811 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.2169. Min Act: -0.1700
Data Index: 7545258 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.2169. Min Act: -0.1700
Data Index: 14849 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.1856. Min Act: -0.1700
Data Index: 1537735 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.1856. Min Act: -0.1700
Data Index: 2454127 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.1856. Min Act: -0.1700
Data Index: 4792901 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5294. Min Range: -5.5294
Max Act: 5.1856. Min Act: -0.1700
Data Index: 1647771 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19