Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 361 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.4876. Min Act: -0.1700
Data Index: 4952140 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.4563. Min Act: -0.1700
Data Index: 789963 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.4251. Min Act: -0.1700
Data Index: 4895839 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3938. Min Act: -0.1700
Data Index: 2549253 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3626. Min Act: -0.1700
Data Index: 4634161 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3626. Min Act: -0.1700
Data Index: 1693112 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3626. Min Act: -0.1700
Data Index: 8814215 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3313. Min Act: -0.1699
Data Index: 4201146 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3626. Min Act: -0.1700
Data Index: 3892993 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3313. Min Act: -0.1700
Data Index: 3205726 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3313. Min Act: -0.1700
Data Index: 3194979 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3313. Min Act: -0.1700
Data Index: 3172651 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3313. Min Act: -0.1700
Data Index: 3197635 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3313. Min Act: -0.1700
Data Index: 3109795 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3313. Min Act: -0.1700
Data Index: 7358354 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3313. Min Act: -0.1698
Data Index: 7326778 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3313. Min Act: -0.1700
Data Index: 8610203 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3313. Min Act: -0.1700
Data Index: 6590274 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3313. Min Act: -0.1700
Data Index: 5364583 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4876. Min Range: -4.4876
Max Act: 4.3313. Min Act: -0.1700
Data Index: 1724888 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19