Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1427. Min Range: -6.1427
Max Act: 6.1427. Min Act: -0.1700
Data Index: 1202851 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1427. Min Range: -6.1427
Max Act: 6.0177. Min Act: -0.1700
Data Index: 1749094 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.9864. Min Act: -0.1700
Data Index: 8823370 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.9552. Min Act: -0.1700
Data Index: 1595232 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.9552. Min Act: -0.1700
Data Index: 3048522 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.9239. Min Act: -0.1700
Data Index: 5130811 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.9239. Min Act: -0.1700
Data Index: 4061327 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.8927. Min Act: -0.1700
Data Index: 2666902 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.8927. Min Act: -0.1700
Data Index: 2962051 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.8614. Min Act: -0.1700
Data Index: 4104384 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.8614. Min Act: -0.1700
Data Index: 32268 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.8614. Min Act: -0.1700
Data Index: 195887 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.8302. Min Act: -0.1700
Data Index: 5916855 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.8302. Min Act: -0.1700
Data Index: 2297338 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.7989. Min Act: -0.1700
Data Index: 4819872 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.7989. Min Act: -0.1700
Data Index: 5557123 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.7989. Min Act: -0.1700
Data Index: 8455848 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.7989. Min Act: -0.1700
Data Index: 2621704 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.7989. Min Act: -0.1700
Data Index: 7603480 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1427. Min Range: -6.1427
Max Act: 5.7989. Min Act: -0.1700
Data Index: 5823036 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19