Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3932. Min Range: -7.3932
Max Act: 7.3620. Min Act: -0.1700
Data Index: 4795240 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3932. Min Range: -7.3932
Max Act: 7.3932. Min Act: -0.1700
Data Index: 3027106 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3932. Min Range: -7.3932
Max Act: 7.2057. Min Act: -0.1700
Data Index: 7514380 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3932. Min Range: -7.3932
Max Act: 7.1432. Min Act: -0.1700
Data Index: 6997933 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3932. Min Range: -7.3932
Max Act: 7.0495. Min Act: -0.1700
Data Index: 3190511 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.9245. Min Act: -0.1700
Data Index: 5838440 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.9870. Min Act: -0.1700
Data Index: 640918 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.9557. Min Act: -0.1700
Data Index: 8340464 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.9245. Min Act: -0.1700
Data Index: 7366347 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.9557. Min Act: -0.1700
Data Index: 7514384 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.8620. Min Act: -0.1700
Data Index: 8097025 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.8932. Min Act: -0.1700
Data Index: 3006933 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.8307. Min Act: -0.1700
Data Index: 4624291 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.9245. Min Act: -0.1700
Data Index: 878536 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.8932. Min Act: -0.1700
Data Index: 1319899 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.8932. Min Act: -0.1700
Data Index: 6135399 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.8307. Min Act: -0.1700
Data Index: 4790625 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.8307. Min Act: -0.1700
Data Index: 6209880 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.8307. Min Act: -0.1700
Data Index: 6835760 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3932. Min Range: -7.3932
Max Act: 6.8307. Min Act: -0.1700
Data Index: 8692336 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19