Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5770 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.6568. Min Act: -0.1700
Data Index: 3356702 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.3443. Min Act: -0.1700
Data Index: 2550047 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.3756. Min Act: -0.1700
Data Index: 5668289 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.3131. Min Act: -0.1700
Data Index: 5436728 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.3131. Min Act: -0.1700
Data Index: 3069785 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.3131. Min Act: -0.1700
Data Index: 4880164 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.3131. Min Act: -0.1700
Data Index: 2550048 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.3443. Min Act: -0.1700
Data Index: 6278624 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.2818. Min Act: -0.1700
Data Index: 7297270 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.2818. Min Act: -0.1700
Data Index: 6909207 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.2193. Min Act: -0.1700
Data Index: 4648942 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.2506. Min Act: -0.1700
Data Index: 7294459 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.2193. Min Act: -0.1700
Data Index: 7573055 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.2193. Min Act: -0.1700
Data Index: 3069786 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.2193. Min Act: -0.1700
Data Index: 6278630 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.1881. Min Act: -0.1700
Data Index: 3069790 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.1881. Min Act: -0.1700
Data Index: 6635759 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.1881. Min Act: -0.1700
Data Index: 487171 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.1881. Min Act: -0.1700
Data Index: 2884225 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6568. Min Range: -5.6568
Max Act: 5.1881. Min Act: -0.1700
Data Index: 4816488 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19