Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5819. Min Range: -6.5819
Max Act: 6.5819. Min Act: -0.1700
Data Index: 6075855 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5819. Min Range: -6.5819
Max Act: 6.3319. Min Act: -0.1700
Data Index: 3073180 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5819. Min Range: -6.5819
Max Act: 6.1756. Min Act: -0.1700
Data Index: 1114802 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5819. Min Range: -6.5819
Max Act: 6.1444. Min Act: -0.1700
Data Index: 8824044 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5819. Min Range: -6.5819
Max Act: 6.0819. Min Act: -0.1700
Data Index: 2235051 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.9881. Min Act: -0.1700
Data Index: 6032094 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.9256. Min Act: -0.1700
Data Index: 6682882 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.8944. Min Act: -0.1700
Data Index: 1830312 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.7381. Min Act: -0.1700
Data Index: 7579864 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.7694. Min Act: -0.1700
Data Index: 1531138 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.7381. Min Act: -0.1700
Data Index: 8091990 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.7381. Min Act: -0.1700
Data Index: 7224814 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.7069. Min Act: -0.1700
Data Index: 3346624 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.7381. Min Act: -0.1700
Data Index: 167940 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.7069. Min Act: -0.1700
Data Index: 721158 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.7069. Min Act: -0.1700
Data Index: 6484409 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.6444. Min Act: -0.1700
Data Index: 345294 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.6756. Min Act: -0.1700
Data Index: 6767097 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.6444. Min Act: -0.1700
Data Index: 2086800 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5819. Min Range: -6.5819
Max Act: 5.6444. Min Act: -0.1700
Data Index: 7414136 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19