Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3245 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2036. Min Range: -7.2036
Max Act: 7.2036. Min Act: -0.1700
Data Index: 5573021 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.9849. Min Act: -0.1700
Data Index: 4895987 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.9224. Min Act: -0.1700
Data Index: 3349620 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.8911. Min Act: -0.1700
Data Index: 6434672 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.8911. Min Act: -0.1700
Data Index: 6673631 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.8599. Min Act: -0.1700
Data Index: 7520149 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.8286. Min Act: -0.1700
Data Index: 4826879 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.7974. Min Act: -0.1700
Data Index: 4082259 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.7349. Min Act: -0.1700
Data Index: 1282436 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.7349. Min Act: -0.1700
Data Index: 4541058 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.7349. Min Act: -0.1700
Data Index: 3058551 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.7036. Min Act: -0.1700
Data Index: 7520141 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.7036. Min Act: -0.1700
Data Index: 5883242 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.7036. Min Act: -0.1700
Data Index: 8715210 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.6724. Min Act: -0.1700
Data Index: 2194352 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.6724. Min Act: -0.1700
Data Index: 5092677 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.6724. Min Act: -0.1700
Data Index: 7317838 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.6411. Min Act: -0.1700
Data Index: 3355327 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.6099. Min Act: -0.1700
Data Index: 780526 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2036. Min Range: -7.2036
Max Act: 6.6411. Min Act: -0.1700
Data Index: 1227865 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19