Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1648. Min Range: -5.1648
Max Act: 5.1648. Min Act: -0.1700
Data Index: 2245132 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1648. Min Range: -5.1648
Max Act: 5.1023. Min Act: -0.1700
Data Index: 5238371 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1648. Min Range: -5.1648
Max Act: 5.0398. Min Act: -0.1700
Data Index: 4808179 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.9461. Min Act: -0.1700
Data Index: 7026427 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.9148. Min Act: -0.1700
Data Index: 1691972 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.9148. Min Act: -0.1700
Data Index: 6026090 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.8836. Min Act: -0.1700
Data Index: 3805268 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.8836. Min Act: -0.1700
Data Index: 4207787 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.8836. Min Act: -0.1700
Data Index: 1635539 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.8836. Min Act: -0.1700
Data Index: 3451820 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.8523. Min Act: -0.1700
Data Index: 3616245 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.8523. Min Act: -0.1700
Data Index: 1802409 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.7898. Min Act: -0.1700
Data Index: 4840840 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.7898. Min Act: -0.1700
Data Index: 6173100 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.7898. Min Act: -0.1700
Data Index: 8184224 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.7586. Min Act: -0.1700
Data Index: 4312295 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.6961. Min Act: -0.1700
Data Index: 2976984 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.7586. Min Act: -0.1700
Data Index: 928397 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.6961. Min Act: -0.1700
Data Index: 7940151 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.6961. Min Act: -0.1700
Data Index: 1350964 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19