Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3271 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.6705. Min Act: -0.1700
Data Index: 8277616 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.6444. Min Act: -0.1700
Data Index: 4410528 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.6183. Min Act: -0.1700
Data Index: 7678370 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.6183. Min Act: -0.1700
Data Index: 1785647 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.6096. Min Act: -0.1700
Data Index: 2232519 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5834. Min Act: -0.1700
Data Index: 3133620 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5746. Min Act: -0.1700
Data Index: 1653575 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5834. Min Act: -0.1700
Data Index: 3689383 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5659. Min Act: -0.1700
Data Index: 7396970 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5659. Min Act: -0.1700
Data Index: 5501999 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5571. Min Act: -0.1700
Data Index: 5320274 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5659. Min Act: -0.1697
Data Index: 8729148 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5484. Min Act: -0.1700
Data Index: 3215283 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5484. Min Act: -0.1700
Data Index: 3609569 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5571. Min Act: -0.1700
Data Index: 6326253 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5484. Min Act: -0.1700
Data Index: 6381597 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5396. Min Act: -0.1700
Data Index: 7524076 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5309. Min Act: -0.1699
Data Index: 2399582 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5396. Min Act: -0.1700
Data Index: 6242717 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6705. Min Range: -1.6705
Max Act: 1.5396. Min Act: -0.1700
Data Index: 6422799 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19