Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4063 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1386. Min Range: -6.1386
Max Act: 6.1386. Min Act: -0.1700
Data Index: 5906641 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1386. Min Range: -6.1386
Max Act: 6.1386. Min Act: -0.1700
Data Index: 3644870 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1386. Min Range: -6.1386
Max Act: 6.1386. Min Act: -0.1700
Data Index: 2783132 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1386. Min Range: -6.1386
Max Act: 6.1386. Min Act: -0.1700
Data Index: 7724818 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1386. Min Range: -6.1386
Max Act: 6.1073. Min Act: -0.1700
Data Index: 7289163 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1386. Min Range: -6.1386
Max Act: 6.0761. Min Act: -0.1700
Data Index: 4752026 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1386. Min Range: -6.1386
Max Act: 6.0448. Min Act: -0.1700
Data Index: 7393975 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1386. Min Range: -6.1386
Max Act: 5.9823. Min Act: -0.1700
Data Index: 5495797 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1386. Min Range: -6.1386
Max Act: 6.0136. Min Act: -0.1700
Data Index: 6430924 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1386. Min Range: -6.1386
Max Act: 5.9823. Min Act: -0.1700
Data Index: 3396098 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1386. Min Range: -6.1386
Max Act: 5.9823. Min Act: -0.1700
Data Index: 1805487 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1386. Min Range: -6.1386
Max Act: 6.0136. Min Act: -0.1700
Data Index: 3011811 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1386. Min Range: -6.1386
Max Act: 5.9823. Min Act: -0.1700
Data Index: 784910 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1386. Min Range: -6.1386
Max Act: 5.9823. Min Act: -0.1700
Data Index: 2086264 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1386. Min Range: -6.1386
Max Act: 5.9511. Min Act: -0.1700
Data Index: 6028269 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1386. Min Range: -6.1386
Max Act: 5.9511. Min Act: -0.1700
Data Index: 1518020 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1386. Min Range: -6.1386
Max Act: 5.9511. Min Act: -0.1700
Data Index: 3532209 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1386. Min Range: -6.1386
Max Act: 5.9511. Min Act: -0.1700
Data Index: 4239854 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1386. Min Range: -6.1386
Max Act: 5.9198. Min Act: -0.1700
Data Index: 3806136 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1386. Min Range: -6.1386
Max Act: 5.8886. Min Act: -0.1700
Data Index: 2753938 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19