Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0334. Min Range: -7.0334
Max Act: 7.0334. Min Act: -0.1700
Data Index: 4894516 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.7522. Min Act: -0.1700
Data Index: 5384247 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.6897. Min Act: -0.1700
Data Index: 4496060 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.5647. Min Act: -0.1700
Data Index: 628477 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.5647. Min Act: -0.1700
Data Index: 2361052 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.5647. Min Act: -0.1700
Data Index: 6876823 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.5334. Min Act: -0.1700
Data Index: 3643553 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.5334. Min Act: -0.1700
Data Index: 251076 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.5334. Min Act: -0.1700
Data Index: 6049543 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.5022. Min Act: -0.1700
Data Index: 3787135 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.4397. Min Act: -0.1700
Data Index: 6801097 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.4084. Min Act: -0.1700
Data Index: 8273343 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.4084. Min Act: -0.1700
Data Index: 4519661 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.3772. Min Act: -0.1700
Data Index: 1466713 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.3772. Min Act: -0.1700
Data Index: 3476310 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.3772. Min Act: -0.1700
Data Index: 6367781 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.3459. Min Act: -0.1700
Data Index: 3202669 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.3147. Min Act: -0.1700
Data Index: 4739490 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.3459. Min Act: -0.1700
Data Index: 1679945 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0334. Min Range: -7.0334
Max Act: 6.3459. Min Act: -0.1700
Data Index: 7583066 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19