Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3885 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6233. Min Range: -8.6233
Max Act: 8.6233. Min Act: -0.1700
Data Index: 7233049 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6233. Min Range: -8.6233
Max Act: 8.4983. Min Act: -0.1700
Data Index: 8422937 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6233. Min Range: -8.6233
Max Act: 8.4358. Min Act: -0.1700
Data Index: 3263490 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6233. Min Range: -8.6233
Max Act: 8.4983. Min Act: -0.1700
Data Index: 6403862 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6233. Min Range: -8.6233
Max Act: 8.3733. Min Act: -0.1700
Data Index: 7959005 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6233. Min Range: -8.6233
Max Act: 8.3733. Min Act: -0.1700
Data Index: 6493480 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6233. Min Range: -8.6233
Max Act: 8.3108. Min Act: -0.1700
Data Index: 2453609 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6233. Min Range: -8.6233
Max Act: 8.2483. Min Act: -0.1700
Data Index: 6762608 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6233. Min Range: -8.6233
Max Act: 8.2483. Min Act: -0.1700
Data Index: 7436105 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6233. Min Range: -8.6233
Max Act: 8.2483. Min Act: -0.1700
Data Index: 8249393 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6233. Min Range: -8.6233
Max Act: 8.1233. Min Act: -0.1700
Data Index: 1842793 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6233. Min Range: -8.6233
Max Act: 8.0296. Min Act: -0.1700
Data Index: 17816 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6233. Min Range: -8.6233
Max Act: 8.0921. Min Act: -0.1700
Data Index: 1680137 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6233. Min Range: -8.6233
Max Act: 7.9983. Min Act: -0.1700
Data Index: 3816991 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6233. Min Range: -8.6233
Max Act: 7.9983. Min Act: -0.1700
Data Index: 2048183 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6233. Min Range: -8.6233
Max Act: 7.9671. Min Act: -0.1700
Data Index: 84237 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6233. Min Range: -8.6233
Max Act: 7.9358. Min Act: -0.1700
Data Index: 4498379 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6233. Min Range: -8.6233
Max Act: 7.9358. Min Act: -0.1700
Data Index: 4610359 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6233. Min Range: -8.6233
Max Act: 7.9983. Min Act: -0.1700
Data Index: 3379246 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6233. Min Range: -8.6233
Max Act: 7.9671. Min Act: -0.1700
Data Index: 1202859 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19