Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 332 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.7567. Min Act: -0.1700
Data Index: 7658125 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.7247. Min Act: -0.1700
Data Index: 6255074 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.6767. Min Act: -0.1700
Data Index: 7299322 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.6607. Min Act: -0.1700
Data Index: 7423428 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.6607. Min Act: -0.1700
Data Index: 2815737 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.6447. Min Act: -0.1700
Data Index: 896161 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.5964. Min Act: -0.1700
Data Index: 2506421 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.5803. Min Act: -0.1700
Data Index: 520232 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.5803. Min Act: -0.1700
Data Index: 530345 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.5642. Min Act: -0.1700
Data Index: 5619617 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.5803. Min Act: -0.1700
Data Index: 7741533 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.5481. Min Act: -0.1700
Data Index: 7135789 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.5642. Min Act: -0.1700
Data Index: 2882331 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.5481. Min Act: -0.1700
Data Index: 5954287 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.5319. Min Act: -0.1700
Data Index: 6810850 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.5319. Min Act: -0.1699
Data Index: 4368270 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.5319. Min Act: -0.1700
Data Index: 250103 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.5319. Min Act: -0.1700
Data Index: 6714022 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.5157. Min Act: -0.1700
Data Index: 3935910 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7567. Min Range: -2.7567
Max Act: 2.5157. Min Act: -0.1700
Data Index: 6579478 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19