Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2121. Min Range: -3.2121
Max Act: 3.2121. Min Act: -0.1700
Data Index: 5075550 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2121. Min Range: -3.2121
Max Act: 3.1019. Min Act: -0.1700
Data Index: 2591544 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2121. Min Range: -3.2121
Max Act: 3.0862. Min Act: -0.1700
Data Index: 1721690 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2121. Min Range: -3.2121
Max Act: 3.0546. Min Act: -0.1700
Data Index: 2591552 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2121. Min Range: -3.2121
Max Act: 3.0073. Min Act: -0.1700
Data Index: 7824931 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2121. Min Range: -3.2121
Max Act: 3.0388. Min Act: -0.1700
Data Index: 6017021 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2121. Min Range: -3.2121
Max Act: 3.0073. Min Act: -0.1700
Data Index: 5019992 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2121. Min Range: -3.2121
Max Act: 3.0231. Min Act: -0.1700
Data Index: 5467485 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2121. Min Range: -3.2121
Max Act: 2.9915. Min Act: -0.1700
Data Index: 1301898 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2121. Min Range: -3.2121
Max Act: 2.9756. Min Act: -0.1700
Data Index: 1676305 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2121. Min Range: -3.2121
Max Act: 2.9598. Min Act: -0.1700
Data Index: 4335800 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2121. Min Range: -3.2121
Max Act: 2.9598. Min Act: -0.1700
Data Index: 4815312 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2121. Min Range: -3.2121
Max Act: 2.9598. Min Act: -0.1700
Data Index: 2629125 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2121. Min Range: -3.2121
Max Act: 2.9598. Min Act: -0.1700
Data Index: 8339314 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2121. Min Range: -3.2121
Max Act: 2.9440. Min Act: -0.1700
Data Index: 2620340 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2121. Min Range: -3.2121
Max Act: 2.9598. Min Act: -0.1700
Data Index: 2917257 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2121. Min Range: -3.2121
Max Act: 2.9282. Min Act: -0.1700
Data Index: 6872372 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2121. Min Range: -3.2121
Max Act: 2.9123. Min Act: -0.1700
Data Index: 5075557 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2121. Min Range: -3.2121
Max Act: 2.9123. Min Act: -0.1700
Data Index: 13357 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2121. Min Range: -3.2121
Max Act: 2.9282. Min Act: -0.1700
Data Index: 4153432 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19