Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.7341. Min Act: -0.1700
Data Index: 1802196 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.7341. Min Act: -0.1700
Data Index: 6341823 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.6716. Min Act: -0.1700
Data Index: 817 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.6716. Min Act: -0.1700
Data Index: 3660694 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.6716. Min Act: -0.1700
Data Index: 1625776 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.6403. Min Act: -0.1700
Data Index: 4355453 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.6091. Min Act: -0.1700
Data Index: 5356288 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.5466. Min Act: -0.1700
Data Index: 2118659 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.5778. Min Act: -0.1700
Data Index: 1318155 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.5466. Min Act: -0.1700
Data Index: 4044843 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.5466. Min Act: -0.1700
Data Index: 770751 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.5778. Min Act: -0.1700
Data Index: 2469424 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.5153. Min Act: -0.1700
Data Index: 1404155 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.5153. Min Act: -0.1700
Data Index: 4621657 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.5153. Min Act: -0.1700
Data Index: 6913888 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.5153. Min Act: -0.1700
Data Index: 7376799 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.4841. Min Act: -0.1700
Data Index: 772531 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.4841. Min Act: -0.1700
Data Index: 248040 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.4841. Min Act: -0.1700
Data Index: 5939627 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7341. Min Range: -5.7341
Max Act: 5.4528. Min Act: -0.1700
Data Index: 226713 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19