Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0289. Min Range: -2.0289
Max Act: 2.0289. Min Act: -0.1700
Data Index: 2835463 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9783. Min Act: -0.1700
Data Index: 8060480 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9783. Min Act: -0.1700
Data Index: 6214993 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9613. Min Act: -0.1700
Data Index: 2286388 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9698. Min Act: -0.1700
Data Index: 2315715 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9443. Min Act: -0.1700
Data Index: 4341301 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9273. Min Act: -0.1700
Data Index: 6083985 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9273. Min Act: -0.1700
Data Index: 6800891 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9188. Min Act: -0.1700
Data Index: 8448161 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9273. Min Act: -0.1700
Data Index: 5797159 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9188. Min Act: -0.1700
Data Index: 1109213 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9188. Min Act: -0.1700
Data Index: 3494082 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9188. Min Act: -0.1700
Data Index: 3111035 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9018. Min Act: -0.1700
Data Index: 712416 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9103. Min Act: -0.1700
Data Index: 33715 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9018. Min Act: -0.1700
Data Index: 8759645 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9103. Min Act: -0.1700
Data Index: 7086804 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9018. Min Act: -0.1700
Data Index: 6465973 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.8933. Min Act: -0.1700
Data Index: 195540 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0289. Min Range: -2.0289
Max Act: 1.9018. Min Act: -0.1700
Data Index: 376032 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19