Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2585 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.8501. Min Act: -0.1700
Data Index: 3397453 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.6626. Min Act: -0.1700
Data Index: 6461825 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.6939. Min Act: -0.1700
Data Index: 5787638 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.6314. Min Act: -0.1700
Data Index: 2400625 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.5689. Min Act: -0.1700
Data Index: 8126258 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.5376. Min Act: -0.1700
Data Index: 3312274 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.5064. Min Act: -0.1700
Data Index: 6000302 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.5064. Min Act: -0.1700
Data Index: 4079743 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.5376. Min Act: -0.1700
Data Index: 5147114 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.4439. Min Act: -0.1700
Data Index: 3491211 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.4439. Min Act: -0.1700
Data Index: 819428 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.4439. Min Act: -0.1700
Data Index: 4363175 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.4126. Min Act: -0.1700
Data Index: 4983097 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.4126. Min Act: -0.1700
Data Index: 4179906 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.3814. Min Act: -0.1700
Data Index: 419466 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.3814. Min Act: -0.1700
Data Index: 7482409 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.3501. Min Act: -0.1700
Data Index: 5315981 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.3501. Min Act: -0.1700
Data Index: 2670675 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.3814. Min Act: -0.1700
Data Index: 2726755 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8501. Min Range: -4.8501
Max Act: 4.3189. Min Act: -0.1700
Data Index: 3433503 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19