Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 550 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3140. Min Range: -6.3140
Max Act: 6.3140. Min Act: -0.1700
Data Index: 5035865 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3140. Min Range: -6.3140
Max Act: 6.2515. Min Act: -0.1700
Data Index: 5207888 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3140. Min Range: -6.3140
Max Act: 6.1890. Min Act: -0.1700
Data Index: 7257495 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3140. Min Range: -6.3140
Max Act: 6.0953. Min Act: -0.1700
Data Index: 8117681 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3140. Min Range: -6.3140
Max Act: 6.0015. Min Act: -0.1700
Data Index: 5594884 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3140. Min Range: -6.3140
Max Act: 6.0015. Min Act: -0.1700
Data Index: 4215545 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3140. Min Range: -6.3140
Max Act: 5.9703. Min Act: -0.1700
Data Index: 2778303 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3140. Min Range: -6.3140
Max Act: 5.9390. Min Act: -0.1700
Data Index: 8390549 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3140. Min Range: -6.3140
Max Act: 5.9390. Min Act: -0.1700
Data Index: 7693376 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3140. Min Range: -6.3140
Max Act: 5.8765. Min Act: -0.1700
Data Index: 8213527 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3140. Min Range: -6.3140
Max Act: 5.8765. Min Act: -0.1700
Data Index: 4143728 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3140. Min Range: -6.3140
Max Act: 5.8765. Min Act: -0.1700
Data Index: 1931890 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3140. Min Range: -6.3140
Max Act: 5.8765. Min Act: -0.1700
Data Index: 7579711 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3140. Min Range: -6.3140
Max Act: 5.8453. Min Act: -0.1700
Data Index: 7538158 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3140. Min Range: -6.3140
Max Act: 5.8140. Min Act: -0.1700
Data Index: 8398489 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3140. Min Range: -6.3140
Max Act: 5.8140. Min Act: -0.1700
Data Index: 7294608 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3140. Min Range: -6.3140
Max Act: 5.8140. Min Act: -0.1700
Data Index: 1338586 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3140. Min Range: -6.3140
Max Act: 5.7828. Min Act: -0.1700
Data Index: 7119164 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3140. Min Range: -6.3140
Max Act: 5.7515. Min Act: -0.1700
Data Index: 6456773 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3140. Min Range: -6.3140
Max Act: 5.7515. Min Act: -0.1700
Data Index: 7258663 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19