Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.9671. Min Act: -0.1700
Data Index: 409082 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.5296. Min Act: -0.1700
Data Index: 1039262 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.4671. Min Act: -0.1700
Data Index: 7960919 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.4671. Min Act: -0.1700
Data Index: 6837882 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.4671. Min Act: -0.1700
Data Index: 1863944 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.4671. Min Act: -0.1700
Data Index: 7822084 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.4046. Min Act: -0.1700
Data Index: 7358382 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.4046. Min Act: -0.1700
Data Index: 4524731 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.3421. Min Act: -0.1700
Data Index: 3578394 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.2796. Min Act: -0.1700
Data Index: 4138807 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.2796. Min Act: -0.1700
Data Index: 2448702 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.2796. Min Act: -0.1700
Data Index: 4275271 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.2171. Min Act: -0.1700
Data Index: 6378454 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.2171. Min Act: -0.1700
Data Index: 802333 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.1546. Min Act: -0.1700
Data Index: 2214230 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.1546. Min Act: -0.1700
Data Index: 8587221 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.0921. Min Act: -0.1700
Data Index: 4905595 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.0921. Min Act: -0.1700
Data Index: 5341572 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.0921. Min Act: -0.1700
Data Index: 4969459 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9671. Min Range: -8.9671
Max Act: 8.0296. Min Act: -0.1700
Data Index: 4337483 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19