Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3447 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4965. Min Range: -7.4965
Max Act: 7.4340. Min Act: -0.1700
Data Index: 5763711 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4965. Min Range: -7.4965
Max Act: 7.4965. Min Act: -0.1700
Data Index: 6146007 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.9965. Min Act: -0.1700
Data Index: 6023248 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.9028. Min Act: -0.1700
Data Index: 5133769 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.9028. Min Act: -0.1700
Data Index: 4100811 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.8090. Min Act: -0.1700
Data Index: 6741959 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.7778. Min Act: -0.1700
Data Index: 2817941 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.8090. Min Act: -0.1700
Data Index: 7952933 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.7465. Min Act: -0.1700
Data Index: 400682 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.6840. Min Act: -0.1700
Data Index: 2752156 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.6528. Min Act: -0.1700
Data Index: 3656941 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.5590. Min Act: -0.1700
Data Index: 4100814 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.6215. Min Act: -0.1700
Data Index: 7414898 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.6215. Min Act: -0.1700
Data Index: 4100815 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.5590. Min Act: -0.1700
Data Index: 6045477 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.4965. Min Act: -0.1700
Data Index: 6876795 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.4653. Min Act: -0.1700
Data Index: 2705051 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.4965. Min Act: -0.1700
Data Index: 4723858 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.4965. Min Act: -0.1700
Data Index: 2752160 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.4965. Min Act: -0.1700
Data Index: 4100812 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19