Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 53 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.7806. Min Act: -0.1700
Data Index: 8094331 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.7965. Min Act: -0.1700
Data Index: 2645112 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.7327. Min Act: -0.1700
Data Index: 8378529 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.7167. Min Act: -0.1700
Data Index: 485660 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.7167. Min Act: -0.1700
Data Index: 7064349 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.7167. Min Act: -0.1700
Data Index: 7969738 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.7007. Min Act: -0.1700
Data Index: 242165 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.7007. Min Act: -0.1700
Data Index: 1708641 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.7007. Min Act: -0.1700
Data Index: 3828273 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.6847. Min Act: -0.1700
Data Index: 686452 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.6847. Min Act: -0.1700
Data Index: 757326 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.7007. Min Act: -0.1700
Data Index: 8798470 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.6847. Min Act: -0.1700
Data Index: 5434853 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.6527. Min Act: -0.1700
Data Index: 757324 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.6687. Min Act: -0.1700
Data Index: 5146243 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.6847. Min Act: -0.1700
Data Index: 3310356 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.6847. Min Act: -0.1700
Data Index: 4288607 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.6687. Min Act: -0.1700
Data Index: 6987616 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.6687. Min Act: -0.1700
Data Index: 6749629 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7965. Min Range: -2.7965
Max Act: 2.6687. Min Act: -0.1700
Data Index: 3916080 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19