Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4556 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.9693. Min Act: -0.1700
Data Index: 1706819 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6880. Min Act: -0.1700
Data Index: 1137168 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.5318. Min Act: -0.1700
Data Index: 6857684 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.4380. Min Act: -0.1700
Data Index: 6142066 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.4380. Min Act: -0.1700
Data Index: 1789588 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.4068. Min Act: -0.1700
Data Index: 5956845 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.4068. Min Act: -0.1700
Data Index: 8746558 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3755. Min Act: -0.1700
Data Index: 2947292 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3755. Min Act: -0.1700
Data Index: 229407 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3443. Min Act: -0.1700
Data Index: 6796454 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3755. Min Act: -0.1700
Data Index: 8827850 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3755. Min Act: -0.1700
Data Index: 5982457 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3130. Min Act: -0.1700
Data Index: 1320967 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3130. Min Act: -0.1700
Data Index: 7189571 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.2505. Min Act: -0.1700
Data Index: 4780135 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.2818. Min Act: -0.1700
Data Index: 2924926 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.2818. Min Act: -0.1700
Data Index: 7031714 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.2818. Min Act: -0.1700
Data Index: 7773849 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.2818. Min Act: -0.1700
Data Index: 7086844 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.2193. Min Act: -0.1700
Data Index: 7127016 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19