Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2077 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6069. Min Range: -7.6069
Max Act: 7.6069. Min Act: -0.1700
Data Index: 1985319 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6069. Min Range: -7.6069
Max Act: 7.5444. Min Act: -0.1700
Data Index: 428933 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6069. Min Range: -7.6069
Max Act: 7.5132. Min Act: -0.1700
Data Index: 2587223 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6069. Min Range: -7.6069
Max Act: 7.3882. Min Act: -0.1700
Data Index: 3712452 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6069. Min Range: -7.6069
Max Act: 7.3257. Min Act: -0.1700
Data Index: 4568486 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6069. Min Range: -7.6069
Max Act: 7.2632. Min Act: -0.1700
Data Index: 4920328 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6069. Min Range: -7.6069
Max Act: 7.2319. Min Act: -0.1700
Data Index: 199220 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6069. Min Range: -7.6069
Max Act: 7.0132. Min Act: -0.1700
Data Index: 7032036 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6069. Min Range: -7.6069
Max Act: 7.0132. Min Act: -0.1700
Data Index: 75546 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6069. Min Range: -7.6069
Max Act: 7.0132. Min Act: -0.1700
Data Index: 1524293 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6069. Min Range: -7.6069
Max Act: 7.0132. Min Act: -0.1700
Data Index: 391507 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6069. Min Range: -7.6069
Max Act: 6.9819. Min Act: -0.1700
Data Index: 4920329 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6069. Min Range: -7.6069
Max Act: 6.9194. Min Act: -0.1700
Data Index: 2390270 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6069. Min Range: -7.6069
Max Act: 6.9194. Min Act: -0.1700
Data Index: 346329 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6069. Min Range: -7.6069
Max Act: 6.8882. Min Act: -0.1700
Data Index: 3354544 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6069. Min Range: -7.6069
Max Act: 6.8882. Min Act: -0.1700
Data Index: 688464 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6069. Min Range: -7.6069
Max Act: 6.8257. Min Act: -0.1700
Data Index: 7443776 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6069. Min Range: -7.6069
Max Act: 6.7944. Min Act: -0.1700
Data Index: 3904150 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6069. Min Range: -7.6069
Max Act: 6.7944. Min Act: -0.1700
Data Index: 5095957 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6069. Min Range: -7.6069
Max Act: 6.7632. Min Act: -0.1700
Data Index: 37376 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19