Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6398 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2052. Min Range: -6.2052
Max Act: 6.2052. Min Act: -0.1700
Data Index: 2793440 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2052. Min Range: -6.2052
Max Act: 6.1427. Min Act: -0.1700
Data Index: 8029570 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2052. Min Range: -6.2052
Max Act: 6.0802. Min Act: -0.1700
Data Index: 3647932 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.9864. Min Act: -0.1700
Data Index: 178595 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.9552. Min Act: -0.1700
Data Index: 2609477 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.9239. Min Act: -0.1700
Data Index: 7909853 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.8927. Min Act: -0.1700
Data Index: 841234 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.8927. Min Act: -0.1700
Data Index: 4719220 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.8927. Min Act: -0.1700
Data Index: 6158381 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.8927. Min Act: -0.1700
Data Index: 900766 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.8614. Min Act: -0.1700
Data Index: 4606127 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.8614. Min Act: -0.1700
Data Index: 8121219 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.8302. Min Act: -0.1700
Data Index: 2272218 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.8302. Min Act: -0.1700
Data Index: 1922136 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.7989. Min Act: -0.1700
Data Index: 5526448 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.7989. Min Act: -0.1700
Data Index: 499638 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.7677. Min Act: -0.1700
Data Index: 2218269 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.7989. Min Act: -0.1700
Data Index: 1925578 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.7677. Min Act: -0.1700
Data Index: 289718 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2052. Min Range: -6.2052
Max Act: 5.7364. Min Act: -0.1700
Data Index: 4055258 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19