Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1477 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0413. Min Range: -5.0413
Max Act: 5.0413. Min Act: -0.1700
Data Index: 1324046 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0413. Min Range: -5.0413
Max Act: 5.0413. Min Act: -0.1700
Data Index: 7243741 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9788. Min Act: -0.1700
Data Index: 3757733 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9788. Min Act: -0.1700
Data Index: 7497279 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9788. Min Act: -0.1700
Data Index: 635778 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9476. Min Act: -0.1700
Data Index: 149939 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9476. Min Act: -0.1700
Data Index: 1969497 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9476. Min Act: -0.1700
Data Index: 314525 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9476. Min Act: -0.1700
Data Index: 3425480 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9476. Min Act: -0.1700
Data Index: 7749006 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9476. Min Act: -0.1700
Data Index: 1629107 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9788. Min Act: -0.1700
Data Index: 1090931 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9476. Min Act: -0.1700
Data Index: 5493551 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9788. Min Act: -0.1700
Data Index: 2690033 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9476. Min Act: -0.1700
Data Index: 3571421 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9163. Min Act: -0.1700
Data Index: 677935 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9163. Min Act: -0.1700
Data Index: 1749974 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9163. Min Act: -0.1700
Data Index: 596151 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9163. Min Act: -0.1700
Data Index: 833151 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9163. Min Act: -0.1700
Data Index: 307928 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19