Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1970 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1132. Min Range: -8.1132
Max Act: 8.1132. Min Act: -0.1700
Data Index: 2674077 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.8007. Min Act: -0.1700
Data Index: 7687815 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.7382. Min Act: -0.1700
Data Index: 6558574 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.7069. Min Act: -0.1700
Data Index: 2213054 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.7382. Min Act: -0.1700
Data Index: 7625602 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.6132. Min Act: -0.1700
Data Index: 5447551 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.5507. Min Act: -0.1700
Data Index: 4947750 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.5507. Min Act: -0.1700
Data Index: 6850503 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.5194. Min Act: -0.1700
Data Index: 3830383 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.5507. Min Act: -0.1700
Data Index: 5959817 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.5507. Min Act: -0.1700
Data Index: 6290183 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.5194. Min Act: -0.1700
Data Index: 6307244 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.5194. Min Act: -0.1700
Data Index: 2805671 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.5194. Min Act: -0.1700
Data Index: 2831657 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.4882. Min Act: -0.1700
Data Index: 4660716 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.4882. Min Act: -0.1700
Data Index: 528357 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.4882. Min Act: -0.1700
Data Index: 2166638 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.4257. Min Act: -0.1700
Data Index: 8687726 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.4257. Min Act: -0.1700
Data Index: 5713842 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1132. Min Range: -8.1132
Max Act: 7.4569. Min Act: -0.1700
Data Index: 5193900 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19