Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2251 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3743. Min Range: -9.3743
Max Act: 9.3743. Min Act: -0.1700
Data Index: 5208206 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3743. Min Range: -9.3743
Max Act: 9.3743. Min Act: -0.1700
Data Index: 1557791 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3743. Min Range: -9.3743
Max Act: 9.0618. Min Act: -0.1700
Data Index: 4973809 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3743. Min Range: -9.3743
Max Act: 9.1243. Min Act: -0.1700
Data Index: 3872687 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3743. Min Range: -9.3743
Max Act: 9.0618. Min Act: -0.1700
Data Index: 1457939 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.9993. Min Act: -0.1700
Data Index: 8673498 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.9993. Min Act: -0.1700
Data Index: 339298 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.9368. Min Act: -0.1700
Data Index: 6857503 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.9368. Min Act: -0.1700
Data Index: 3566947 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.8743. Min Act: -0.1700
Data Index: 2554045 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.8118. Min Act: -0.1700
Data Index: 1953273 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.8743. Min Act: -0.1700
Data Index: 2112150 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.8118. Min Act: -0.1700
Data Index: 1343991 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.8118. Min Act: -0.1700
Data Index: 643862 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.8743. Min Act: -0.1700
Data Index: 8233811 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.8118. Min Act: -0.1700
Data Index: 7487522 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.7493. Min Act: -0.1700
Data Index: 2745349 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.8118. Min Act: -0.1700
Data Index: 317136 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.7493. Min Act: -0.1700
Data Index: 2285291 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3743. Min Range: -9.3743
Max Act: 8.8118. Min Act: -0.1700
Data Index: 7882950 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19