Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1832 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.8041. Min Act: -0.1700
Data Index: 3931505 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.7103. Min Act: -0.1700
Data Index: 6065463 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.6166. Min Act: -0.1700
Data Index: 5320854 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.6166. Min Act: -0.1700
Data Index: 4285597 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.5853. Min Act: -0.1700
Data Index: 4267061 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.5541. Min Act: -0.1700
Data Index: 7060214 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.4916. Min Act: -0.1700
Data Index: 7603124 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.4916. Min Act: -0.1700
Data Index: 6846580 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.4916. Min Act: -0.1700
Data Index: 7759781 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.4603. Min Act: -0.1700
Data Index: 5129615 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.4291. Min Act: -0.1700
Data Index: 6535447 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.4603. Min Act: -0.1700
Data Index: 6254167 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.4603. Min Act: -0.1700
Data Index: 2274686 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.4603. Min Act: -0.1700
Data Index: 5440125 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.4291. Min Act: -0.1700
Data Index: 1431707 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.4291. Min Act: -0.1700
Data Index: 4364964 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.4291. Min Act: -0.1700
Data Index: 6554231 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.3978. Min Act: -0.1700
Data Index: 3018778 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.3978. Min Act: -0.1700
Data Index: 3421069 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8041. Min Range: -4.8041
Max Act: 4.3978. Min Act: -0.1700
Data Index: 7036852 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19