Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4448. Min Range: -5.4448
Max Act: 5.4448. Min Act: -0.1700
Data Index: 1964899 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4448. Min Range: -5.4448
Max Act: 5.1948. Min Act: -0.1700
Data Index: 5995113 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4448. Min Range: -5.4448
Max Act: 5.1948. Min Act: -0.1700
Data Index: 8603117 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4448. Min Range: -5.4448
Max Act: 5.1636. Min Act: -0.1700
Data Index: 5344160 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4448. Min Range: -5.4448
Max Act: 5.1948. Min Act: -0.1700
Data Index: 1786687 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4448. Min Range: -5.4448
Max Act: 5.1323. Min Act: -0.1700
Data Index: 2875655 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4448. Min Range: -5.4448
Max Act: 5.1011. Min Act: -0.1700
Data Index: 8365535 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4448. Min Range: -5.4448
Max Act: 5.0386. Min Act: -0.1700
Data Index: 697978 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4448. Min Range: -5.4448
Max Act: 5.0073. Min Act: -0.1700
Data Index: 5180985 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4448. Min Range: -5.4448
Max Act: 5.0073. Min Act: -0.1700
Data Index: 5392538 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4448. Min Range: -5.4448
Max Act: 4.9761. Min Act: -0.1700
Data Index: 3402639 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4448. Min Range: -5.4448
Max Act: 4.9761. Min Act: -0.1700
Data Index: 2927413 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4448. Min Range: -5.4448
Max Act: 4.9761. Min Act: -0.1700
Data Index: 6587931 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4448. Min Range: -5.4448
Max Act: 4.9448. Min Act: -0.1700
Data Index: 6988191 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4448. Min Range: -5.4448
Max Act: 4.9448. Min Act: -0.1700
Data Index: 61337 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4448. Min Range: -5.4448
Max Act: 4.9448. Min Act: -0.1700
Data Index: 5962504 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4448. Min Range: -5.4448
Max Act: 4.9448. Min Act: -0.1700
Data Index: 7394138 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4448. Min Range: -5.4448
Max Act: 4.9448. Min Act: -0.1700
Data Index: 935737 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4448. Min Range: -5.4448
Max Act: 4.9136. Min Act: -0.1700
Data Index: 3202498 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4448. Min Range: -5.4448
Max Act: 4.9136. Min Act: -0.1700
Data Index: 6587932 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19