Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1995 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.7406. Min Act: -0.1700
Data Index: 4099774 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.7093. Min Act: -0.1700
Data Index: 4218963 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.7093. Min Act: -0.1700
Data Index: 4100546 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.7093. Min Act: -0.1700
Data Index: 7188221 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.7093. Min Act: -0.1700
Data Index: 1795305 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.6780. Min Act: -0.1700
Data Index: 7037855 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.6780. Min Act: -0.1700
Data Index: 342961 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.6780. Min Act: -0.1700
Data Index: 8396316 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.6780. Min Act: -0.1700
Data Index: 3969503 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.6467. Min Act: -0.1700
Data Index: 4320842 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.6624. Min Act: -0.1700
Data Index: 8254439 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.6624. Min Act: -0.1700
Data Index: 248588 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.6624. Min Act: -0.1700
Data Index: 1220554 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.6624. Min Act: -0.1700
Data Index: 1326137 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.6311. Min Act: -0.1700
Data Index: 6801428 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.5998. Min Act: -0.1700
Data Index: 4989796 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.6311. Min Act: -0.1700
Data Index: 1135253 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.6311. Min Act: -0.1700
Data Index: 501797 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.6311. Min Act: -0.1700
Data Index: 2439604 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7406. Min Range: -3.7406
Max Act: 3.6154. Min Act: -0.1700
Data Index: 6496677 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19