Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5534 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.6579. Min Act: -0.1700
Data Index: 6768142 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.4704. Min Act: -0.1700
Data Index: 2193196 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.4391. Min Act: -0.1700
Data Index: 7539906 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.4079. Min Act: -0.1700
Data Index: 3698394 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.4391. Min Act: -0.1700
Data Index: 522933 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.4079. Min Act: -0.1700
Data Index: 1602661 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.3766. Min Act: -0.1700
Data Index: 7626687 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.3766. Min Act: -0.1700
Data Index: 8220915 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.3454. Min Act: -0.1700
Data Index: 2997942 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.3454. Min Act: -0.1700
Data Index: 3345536 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.3141. Min Act: -0.1700
Data Index: 4243729 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.3141. Min Act: -0.1700
Data Index: 4121623 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.3141. Min Act: -0.1700
Data Index: 2012112 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.3141. Min Act: -0.1700
Data Index: 3871134 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.3141. Min Act: -0.1700
Data Index: 8285345 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.3141. Min Act: -0.1700
Data Index: 7040144 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.3141. Min Act: -0.1700
Data Index: 6850673 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.3141. Min Act: -0.1700
Data Index: 8036140 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.2829. Min Act: -0.1700
Data Index: 2786774 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6579. Min Range: -4.6579
Max Act: 4.2829. Min Act: -0.1700
Data Index: 798552 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19