Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.3417. Min Act: -0.1700
Data Index: 1719028 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2946. Min Act: -0.1700
Data Index: 6226934 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2003. Min Act: -0.1700
Data Index: 2333597 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1688. Min Act: -0.1700
Data Index: 5055541 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1531. Min Act: -0.1700
Data Index: 3852660 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1531. Min Act: -0.1700
Data Index: 4794098 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1531. Min Act: -0.1700
Data Index: 4455996 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1531. Min Act: -0.1700
Data Index: 6704492 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1531. Min Act: -0.1700
Data Index: 4597879 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1374. Min Act: -0.1700
Data Index: 606353 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1374. Min Act: -0.1700
Data Index: 583674 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1374. Min Act: -0.1700
Data Index: 4619377 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1374. Min Act: -0.1700
Data Index: 1604981 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1216. Min Act: -0.1700
Data Index: 4511332 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1216. Min Act: -0.1700
Data Index: 1699793 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1216. Min Act: -0.1700
Data Index: 6660378 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1059. Min Act: -0.1700
Data Index: 353808 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1059. Min Act: -0.1700
Data Index: 6801321 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1059. Min Act: -0.1700
Data Index: 1986736 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.1059. Min Act: -0.1700
Data Index: 8040164 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19