Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2807 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0837. Min Range: -6.0837
Max Act: 6.0837. Min Act: -0.1700
Data Index: 7621681 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.9587. Min Act: -0.1700
Data Index: 5623172 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.9275. Min Act: -0.1700
Data Index: 7926453 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.8650. Min Act: -0.1700
Data Index: 6988413 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.8337. Min Act: -0.1700
Data Index: 3352421 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.8025. Min Act: -0.1700
Data Index: 5444236 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.8337. Min Act: -0.1700
Data Index: 3274732 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.7712. Min Act: -0.1700
Data Index: 351230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.7712. Min Act: -0.1700
Data Index: 1130850 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.7400. Min Act: -0.1700
Data Index: 7910703 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.7400. Min Act: -0.1700
Data Index: 1583610 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.6775. Min Act: -0.1700
Data Index: 6075035 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.6775. Min Act: -0.1700
Data Index: 5227731 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.6775. Min Act: -0.1700
Data Index: 3423548 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.6775. Min Act: -0.1700
Data Index: 4564208 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.7087. Min Act: -0.1700
Data Index: 8712057 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.6462. Min Act: -0.1700
Data Index: 850173 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.6775. Min Act: -0.1700
Data Index: 6593614 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.6775. Min Act: -0.1700
Data Index: 1211016 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0837. Min Range: -6.0837
Max Act: 5.6462. Min Act: -0.1700
Data Index: 5651397 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19