Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1248 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.5129. Min Act: -0.1700
Data Index: 3325960 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.4602. Min Act: -0.1700
Data Index: 7170312 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.4426. Min Act: -0.1700
Data Index: 7224745 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3722. Min Act: -0.1700
Data Index: 569423 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3722. Min Act: -0.1700
Data Index: 5415304 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3722. Min Act: -0.1700
Data Index: 3874759 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3722. Min Act: -0.1700
Data Index: 6368659 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3545. Min Act: -0.1700
Data Index: 2626980 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3545. Min Act: -0.1700
Data Index: 6061467 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3193. Min Act: -0.1700
Data Index: 7601945 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3369. Min Act: -0.1700
Data Index: 3801448 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3369. Min Act: -0.1700
Data Index: 6211223 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3193. Min Act: -0.1700
Data Index: 768708 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3193. Min Act: -0.1700
Data Index: 6902975 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3193. Min Act: -0.1700
Data Index: 6637338 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3193. Min Act: -0.1700
Data Index: 442076 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3193. Min Act: -0.1700
Data Index: 8611559 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3016. Min Act: -0.1700
Data Index: 6877371 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3016. Min Act: -0.1700
Data Index: 1825616 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5129. Min Range: -1.5129
Max Act: 1.3016. Min Act: -0.1700
Data Index: 4164641 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19