Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 471 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.6446. Min Act: -0.1700
Data Index: 8143691 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.5821. Min Act: -0.1700
Data Index: 3641520 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.5508. Min Act: -0.1700
Data Index: 7192207 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.5821. Min Act: -0.1700
Data Index: 1134598 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4883. Min Act: -0.1700
Data Index: 2141826 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4883. Min Act: -0.1700
Data Index: 2674609 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4883. Min Act: -0.1700
Data Index: 3912599 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4883. Min Act: -0.1700
Data Index: 8324162 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4571. Min Act: -0.1700
Data Index: 3028324 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4258. Min Act: -0.1700
Data Index: 7622235 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4258. Min Act: -0.1700
Data Index: 2973706 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4571. Min Act: -0.1700
Data Index: 2915056 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4571. Min Act: -0.1700
Data Index: 1890220 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4258. Min Act: -0.1700
Data Index: 8518317 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4258. Min Act: -0.1700
Data Index: 5209849 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4258. Min Act: -0.1700
Data Index: 4545684 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4258. Min Act: -0.1700
Data Index: 2746368 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4258. Min Act: -0.1700
Data Index: 417422 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4258. Min Act: -0.1700
Data Index: 7029691 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6446. Min Range: -4.6446
Max Act: 4.4258. Min Act: -0.1700
Data Index: 3226451 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19