Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0140. Min Range: -3.0140
Max Act: 3.0140. Min Act: -0.1699
Data Index: 8043789 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.9666. Min Act: -0.1700
Data Index: 4062020 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.9507. Min Act: -0.1700
Data Index: 3661172 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.9349. Min Act: -0.1700
Data Index: 257181 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.9507. Min Act: -0.1700
Data Index: 7896813 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.8715. Min Act: -0.1700
Data Index: 6546520 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.8556. Min Act: -0.1700
Data Index: 6806162 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.8873. Min Act: -0.1700
Data Index: 2874947 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.8556. Min Act: -0.1700
Data Index: 6977504 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.8397. Min Act: -0.1700
Data Index: 5285040 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.8238. Min Act: -0.1700
Data Index: 5000048 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.8079. Min Act: -0.1700
Data Index: 8719273 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.8079. Min Act: -0.1700
Data Index: 829378 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.8079. Min Act: -0.1700
Data Index: 6729322 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.8079. Min Act: -0.1700
Data Index: 8402220 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.7920. Min Act: -0.1700
Data Index: 8479953 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.7920. Min Act: -0.1700
Data Index: 4676754 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.7920. Min Act: -0.1700
Data Index: 1905221 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.7920. Min Act: -0.1700
Data Index: 6748279 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0140. Min Range: -3.0140
Max Act: 2.7760. Min Act: -0.1700
Data Index: 5018593 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19