Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3276 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1490. Min Range: -7.1490
Max Act: 7.1490. Min Act: -0.1700
Data Index: 960468 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1490. Min Range: -7.1490
Max Act: 7.1177. Min Act: -0.1700
Data Index: 6437385 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1490. Min Range: -7.1490
Max Act: 7.1177. Min Act: -0.1700
Data Index: 94762 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1490. Min Range: -7.1490
Max Act: 7.0865. Min Act: -0.1700
Data Index: 3200817 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1490. Min Range: -7.1490
Max Act: 7.0240. Min Act: -0.1700
Data Index: 7094028 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.9927. Min Act: -0.1700
Data Index: 4765286 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.9927. Min Act: -0.1700
Data Index: 3348637 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.9615. Min Act: -0.1700
Data Index: 4671673 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.9302. Min Act: -0.1700
Data Index: 7258359 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.9302. Min Act: -0.1700
Data Index: 1969325 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.9302. Min Act: -0.1700
Data Index: 1033145 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.9302. Min Act: -0.1700
Data Index: 6866023 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.9302. Min Act: -0.1700
Data Index: 6272458 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.8990. Min Act: -0.1700
Data Index: 1986200 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.8990. Min Act: -0.1700
Data Index: 6892375 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.8677. Min Act: -0.1700
Data Index: 4253542 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.8677. Min Act: -0.1700
Data Index: 1284569 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.8677. Min Act: -0.1700
Data Index: 4442862 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.8990. Min Act: -0.1700
Data Index: 6787824 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1490. Min Range: -7.1490
Max Act: 6.8365. Min Act: -0.1700
Data Index: 4146242 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19