Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2835. Min Range: -8.2835
Max Act: 8.2835. Min Act: -0.1700
Data Index: 1225566 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.9710. Min Act: -0.1700
Data Index: 5463287 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.9085. Min Act: -0.1700
Data Index: 536563 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.8460. Min Act: -0.1700
Data Index: 4476239 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.8460. Min Act: -0.1700
Data Index: 2975824 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.8460. Min Act: -0.1700
Data Index: 6175149 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.6897. Min Act: -0.1700
Data Index: 7931406 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.6272. Min Act: -0.1700
Data Index: 2452565 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.6272. Min Act: -0.1700
Data Index: 3490033 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.5960. Min Act: -0.1700
Data Index: 6281432 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.5960. Min Act: -0.1700
Data Index: 1699314 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.5647. Min Act: -0.1700
Data Index: 1724559 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.5335. Min Act: -0.1700
Data Index: 6858868 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.4710. Min Act: -0.1700
Data Index: 328341 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.4710. Min Act: -0.1700
Data Index: 2682639 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.4397. Min Act: -0.1700
Data Index: 1511520 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.4710. Min Act: -0.1700
Data Index: 6347277 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.4397. Min Act: -0.1700
Data Index: 1918782 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.4710. Min Act: -0.1700
Data Index: 6147743 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2835. Min Range: -8.2835
Max Act: 7.4085. Min Act: -0.1700
Data Index: 2435868 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19