Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.7624. Min Act: -0.1700
Data Index: 4041471 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.4186. Min Act: -0.1700
Data Index: 5719189 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.4499. Min Act: -0.1700
Data Index: 6066533 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.4186. Min Act: -0.1700
Data Index: 3637264 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.3561. Min Act: -0.1700
Data Index: 1437057 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.3561. Min Act: -0.1700
Data Index: 8696189 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.3249. Min Act: -0.1700
Data Index: 8789098 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.2936. Min Act: -0.1700
Data Index: 5922426 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.2311. Min Act: -0.1700
Data Index: 804380 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.2311. Min Act: -0.1700
Data Index: 1017320 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.2624. Min Act: -0.1700
Data Index: 1132386 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.2311. Min Act: -0.1700
Data Index: 2186337 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.1999. Min Act: -0.1700
Data Index: 1132381 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.1999. Min Act: -0.1700
Data Index: 7658902 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.2311. Min Act: -0.1700
Data Index: 5685651 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.1686. Min Act: -0.1700
Data Index: 3968940 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.1374. Min Act: -0.1700
Data Index: 7605497 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.1374. Min Act: -0.1700
Data Index: 2314779 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.0749. Min Act: -0.1700
Data Index: 5171295 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7624. Min Range: -5.7624
Max Act: 5.1374. Min Act: -0.1700
Data Index: 1274709 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19