Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1361 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.2576. Min Act: -0.1700
Data Index: 4717626 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.1326. Min Act: -0.1700
Data Index: 4061260 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.1326. Min Act: -0.1700
Data Index: 1561279 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0701. Min Act: -0.1700
Data Index: 2061927 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0701. Min Act: -0.1700
Data Index: 3846947 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0701. Min Act: -0.1700
Data Index: 3017524 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0388. Min Act: -0.1700
Data Index: 484313 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0388. Min Act: -0.1700
Data Index: 3461842 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0388. Min Act: -0.1700
Data Index: 5086174 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0388. Min Act: -0.1700
Data Index: 3100575 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0388. Min Act: -0.1700
Data Index: 6733713 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0075. Min Act: -0.1700
Data Index: 3542554 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2576. Min Range: -4.2576
Max Act: 3.9763. Min Act: -0.1700
Data Index: 4631476 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2576. Min Range: -4.2576
Max Act: 3.9763. Min Act: -0.1700
Data Index: 5508911 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2576. Min Range: -4.2576
Max Act: 3.9763. Min Act: -0.1700
Data Index: 8492220 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2576. Min Range: -4.2576
Max Act: 3.9450. Min Act: -0.1700
Data Index: 4062203 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2576. Min Range: -4.2576
Max Act: 3.9450. Min Act: -0.1700
Data Index: 7106325 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2576. Min Range: -4.2576
Max Act: 3.9450. Min Act: -0.1700
Data Index: 4419593 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2576. Min Range: -4.2576
Max Act: 3.9450. Min Act: -0.1700
Data Index: 4701505 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2576. Min Range: -4.2576
Max Act: 3.9137. Min Act: -0.1700
Data Index: 6766366 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19