Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 922 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.8286. Min Act: -0.1700
Data Index: 3936295 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.7809. Min Act: -0.1700
Data Index: 38632 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.7809. Min Act: -0.1700
Data Index: 8483007 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.7490. Min Act: -0.1700
Data Index: 8539962 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.7490. Min Act: -0.1700
Data Index: 1013264 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.7490. Min Act: -0.1700
Data Index: 8291948 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.7330. Min Act: -0.1700
Data Index: 7798785 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.7330. Min Act: -0.1700
Data Index: 5303398 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.7170. Min Act: -0.1700
Data Index: 3962743 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.7170. Min Act: -0.1700
Data Index: 1314997 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.7010. Min Act: -0.1700
Data Index: 6502271 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.6850. Min Act: -0.1700
Data Index: 2258902 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.6369. Min Act: -0.1700
Data Index: 7726718 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.6690. Min Act: -0.1700
Data Index: 2865565 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.6690. Min Act: -0.1700
Data Index: 5729112 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.6529. Min Act: -0.1700
Data Index: 7075589 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.6529. Min Act: -0.1700
Data Index: 3219899 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.6690. Min Act: -0.1700
Data Index: 5334051 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.6369. Min Act: -0.1700
Data Index: 7827948 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8286. Min Range: -2.8286
Max Act: 2.6208. Min Act: -0.1700
Data Index: 7480278 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19