Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4212 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0422. Min Range: -11.0422
Max Act: 11.0422. Min Act: -0.1700
Data Index: 3147260 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0422. Min Range: -11.0422
Max Act: 10.9172. Min Act: -0.1700
Data Index: 6278431 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0422. Min Range: -11.0422
Max Act: 10.9172. Min Act: -0.1700
Data Index: 4647318 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0422. Min Range: -11.0422
Max Act: 10.6047. Min Act: -0.1700
Data Index: 3469222 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0422. Min Range: -11.0422
Max Act: 10.5422. Min Act: -0.1700
Data Index: 6182716 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0422. Min Range: -11.0422
Max Act: 10.2297. Min Act: -0.1700
Data Index: 7473604 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0422. Min Range: -11.0422
Max Act: 10.2297. Min Act: -0.1700
Data Index: 5068758 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0422. Min Range: -11.0422
Max Act: 10.1672. Min Act: -0.1700
Data Index: 6544539 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0422. Min Range: -11.0422
Max Act: 10.1672. Min Act: -0.1700
Data Index: 4397725 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0422. Min Range: -11.0422
Max Act: 10.1672. Min Act: -0.1700
Data Index: 3570391 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0422. Min Range: -11.0422
Max Act: 10.1672. Min Act: -0.1700
Data Index: 1143593 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0422. Min Range: -11.0422
Max Act: 10.1047. Min Act: -0.1700
Data Index: 7016054 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0422. Min Range: -11.0422
Max Act: 10.1047. Min Act: -0.1700
Data Index: 2062306 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0422. Min Range: -11.0422
Max Act: 9.9797. Min Act: -0.1700
Data Index: 8640662 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0422. Min Range: -11.0422
Max Act: 9.9797. Min Act: -0.1700
Data Index: 310742 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0422. Min Range: -11.0422
Max Act: 9.9797. Min Act: -0.1700
Data Index: 5744378 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0422. Min Range: -11.0422
Max Act: 9.9797. Min Act: -0.1700
Data Index: 7633116 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0422. Min Range: -11.0422
Max Act: 9.9172. Min Act: -0.1700
Data Index: 5790335 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0422. Min Range: -11.0422
Max Act: 9.9172. Min Act: -0.1700
Data Index: 36502 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0422. Min Range: -11.0422
Max Act: 9.9172. Min Act: -0.1700
Data Index: 4809637 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19