Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0304. Min Range: -4.0304
Max Act: 4.0304. Min Act: -0.1700
Data Index: 542132 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.8428. Min Act: -0.1700
Data Index: 2257577 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.8115. Min Act: -0.1700
Data Index: 2687951 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.7803. Min Act: -0.1700
Data Index: 7938127 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.7803. Min Act: -0.1700
Data Index: 5700091 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.7490. Min Act: -0.1700
Data Index: 7935382 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.7177. Min Act: -0.1700
Data Index: 6249063 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.6708. Min Act: -0.1700
Data Index: 2993956 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.6708. Min Act: -0.1700
Data Index: 198168 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.6708. Min Act: -0.1700
Data Index: 3521250 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.6551. Min Act: -0.1700
Data Index: 8681406 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.6708. Min Act: -0.1700
Data Index: 1130837 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.6395. Min Act: -0.1700
Data Index: 281594 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.6395. Min Act: -0.1700
Data Index: 5782140 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.6395. Min Act: -0.1700
Data Index: 1779687 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.6238. Min Act: -0.1700
Data Index: 5744428 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.6238. Min Act: -0.1700
Data Index: 1130843 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.5925. Min Act: -0.1700
Data Index: 1429767 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.5925. Min Act: -0.1700
Data Index: 2014197 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0304. Min Range: -4.0304
Max Act: 3.5925. Min Act: -0.1700
Data Index: 3281676 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19