Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4264 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.6584. Min Act: -0.1700
Data Index: 5623100 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.5959. Min Act: -0.1700
Data Index: 8600088 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.4084. Min Act: -0.1700
Data Index: 1100202 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.3147. Min Act: -0.1700
Data Index: 8642223 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.3459. Min Act: -0.1700
Data Index: 5623094 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.3147. Min Act: -0.1700
Data Index: 4998663 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.2522. Min Act: -0.1700
Data Index: 1100203 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.2209. Min Act: -0.1700
Data Index: 7209532 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.2209. Min Act: -0.1700
Data Index: 2652582 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.1897. Min Act: -0.1700
Data Index: 4002906 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.0959. Min Act: -0.1700
Data Index: 3646534 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.0959. Min Act: -0.1700
Data Index: 1971864 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.0959. Min Act: -0.1700
Data Index: 8121111 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.0959. Min Act: -0.1700
Data Index: 1575817 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.0647. Min Act: -0.1700
Data Index: 5266829 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.0334. Min Act: -0.1700
Data Index: 985469 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.0334. Min Act: -0.1700
Data Index: 2478311 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.0334. Min Act: -0.1700
Data Index: 1873620 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.0334. Min Act: -0.1700
Data Index: 937301 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6584. Min Range: -6.6584
Max Act: 6.0334. Min Act: -0.1700
Data Index: 4683625 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19