Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5575 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1224. Min Range: -5.1224
Max Act: 5.1224. Min Act: -0.1700
Data Index: 1242759 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1224. Min Range: -5.1224
Max Act: 5.0911. Min Act: -0.1700
Data Index: 996879 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.9974. Min Act: -0.1700
Data Index: 5142455 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.8724. Min Act: -0.1700
Data Index: 4926062 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.8724. Min Act: -0.1700
Data Index: 6861165 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.8724. Min Act: -0.1700
Data Index: 4256060 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.8724. Min Act: -0.1700
Data Index: 2356189 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.8724. Min Act: -0.1700
Data Index: 3514607 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.8724. Min Act: -0.1700
Data Index: 8806015 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.8411. Min Act: -0.1700
Data Index: 3211981 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.8411. Min Act: -0.1700
Data Index: 8337633 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.8099. Min Act: -0.1700
Data Index: 574328 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.8099. Min Act: -0.1700
Data Index: 2384138 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.7786. Min Act: -0.1700
Data Index: 144687 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.7786. Min Act: -0.1700
Data Index: 4678207 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.7786. Min Act: -0.1700
Data Index: 83927 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.7786. Min Act: -0.1700
Data Index: 7928064 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.7786. Min Act: -0.1700
Data Index: 7413688 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.7786. Min Act: -0.1700
Data Index: 3299093 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1224. Min Range: -5.1224
Max Act: 4.7474. Min Act: -0.1700
Data Index: 5837651 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19