Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2485. Min Range: -7.2485
Max Act: 7.2485. Min Act: -0.1700
Data Index: 3613183 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2485. Min Range: -7.2485
Max Act: 7.2172. Min Act: -0.1700
Data Index: 4641900 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2485. Min Range: -7.2485
Max Act: 7.1547. Min Act: -0.1700
Data Index: 6513024 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2485. Min Range: -7.2485
Max Act: 7.1547. Min Act: -0.1700
Data Index: 1978336 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2485. Min Range: -7.2485
Max Act: 7.1235. Min Act: -0.1700
Data Index: 5349489 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2485. Min Range: -7.2485
Max Act: 7.1235. Min Act: -0.1700
Data Index: 2257021 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2485. Min Range: -7.2485
Max Act: 7.1235. Min Act: -0.1700
Data Index: 2470558 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2485. Min Range: -7.2485
Max Act: 7.0297. Min Act: -0.1700
Data Index: 8685909 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2485. Min Range: -7.2485
Max Act: 7.0297. Min Act: -0.1700
Data Index: 1024199 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2485. Min Range: -7.2485
Max Act: 7.0297. Min Act: -0.1700
Data Index: 7096422 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2485. Min Range: -7.2485
Max Act: 7.0297. Min Act: -0.1700
Data Index: 2055197 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.9985. Min Act: -0.1700
Data Index: 7297179 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.9360. Min Act: -0.1700
Data Index: 7132952 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.9672. Min Act: -0.1700
Data Index: 6720435 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.9360. Min Act: -0.1700
Data Index: 7439491 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.9047. Min Act: -0.1700
Data Index: 7066304 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.9047. Min Act: -0.1700
Data Index: 7193783 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.8735. Min Act: -0.1700
Data Index: 8157012 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.8422. Min Act: -0.1700
Data Index: 1664030 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.8422. Min Act: -0.1700
Data Index: 4774332 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19