Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3136. Min Range: -8.3136
Max Act: 8.3136. Min Act: -0.1700
Data Index: 1775580 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3136. Min Range: -8.3136
Max Act: 8.1261. Min Act: -0.1700
Data Index: 5826762 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3136. Min Range: -8.3136
Max Act: 8.1261. Min Act: -0.1700
Data Index: 1216618 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3136. Min Range: -8.3136
Max Act: 8.0011. Min Act: -0.1700
Data Index: 5061235 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.9386. Min Act: -0.1700
Data Index: 4224917 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.9386. Min Act: -0.1700
Data Index: 8475952 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.8136. Min Act: -0.1700
Data Index: 5399898 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.7511. Min Act: -0.1700
Data Index: 2264426 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.7511. Min Act: -0.1700
Data Index: 7299762 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.6886. Min Act: -0.1700
Data Index: 6583796 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.6886. Min Act: -0.1700
Data Index: 7761454 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.6261. Min Act: -0.1700
Data Index: 6139648 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.6261. Min Act: -0.1700
Data Index: 3339159 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.5948. Min Act: -0.1700
Data Index: 463604 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.5323. Min Act: -0.1700
Data Index: 6730047 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.5636. Min Act: -0.1700
Data Index: 6254254 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.5636. Min Act: -0.1700
Data Index: 6235452 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.5636. Min Act: -0.1700
Data Index: 334322 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.5323. Min Act: -0.1700
Data Index: 6882934 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3136. Min Range: -8.3136
Max Act: 7.5011. Min Act: -0.1700
Data Index: 4315169 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19