Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3378 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1297. Min Range: -8.1297
Max Act: 8.1297. Min Act: -0.1700
Data Index: 5208736 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.4422. Min Act: -0.1700
Data Index: 8729539 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.3797. Min Act: -0.1700
Data Index: 3154000 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.3797. Min Act: -0.1700
Data Index: 4276541 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.3172. Min Act: -0.1700
Data Index: 4909680 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.3172. Min Act: -0.1700
Data Index: 8349900 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.2547. Min Act: -0.1700
Data Index: 7124129 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.2547. Min Act: -0.1700
Data Index: 4155953 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.1922. Min Act: -0.1700
Data Index: 900095 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.1922. Min Act: -0.1700
Data Index: 4458461 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.1922. Min Act: -0.1700
Data Index: 7771044 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.1922. Min Act: -0.1700
Data Index: 499440 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.1609. Min Act: -0.1700
Data Index: 829205 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.1609. Min Act: -0.1700
Data Index: 5538406 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.1609. Min Act: -0.1700
Data Index: 2633851 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.0984. Min Act: -0.1700
Data Index: 932822 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.1297. Min Act: -0.1700
Data Index: 5056964 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.1297. Min Act: -0.1700
Data Index: 6581830 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.0984. Min Act: -0.1700
Data Index: 4839915 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1297. Min Range: -8.1297
Max Act: 7.1297. Min Act: -0.1700
Data Index: 6014965 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19