Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 983 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6481. Min Range: -7.6481
Max Act: 7.6481. Min Act: -0.1700
Data Index: 3883051 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6481. Min Range: -7.6481
Max Act: 7.3981. Min Act: -0.1700
Data Index: 4411339 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6481. Min Range: -7.6481
Max Act: 7.3044. Min Act: -0.1700
Data Index: 13467 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6481. Min Range: -7.6481
Max Act: 7.1794. Min Act: -0.1700
Data Index: 8560673 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6481. Min Range: -7.6481
Max Act: 7.1169. Min Act: -0.1700
Data Index: 2042306 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6481. Min Range: -7.6481
Max Act: 7.0231. Min Act: -0.1700
Data Index: 8656960 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6481. Min Range: -7.6481
Max Act: 7.0231. Min Act: -0.1700
Data Index: 6895521 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6481. Min Range: -7.6481
Max Act: 7.0231. Min Act: -0.1700
Data Index: 6390725 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6481. Min Range: -7.6481
Max Act: 6.9919. Min Act: -0.1700
Data Index: 503008 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6481. Min Range: -7.6481
Max Act: 6.9919. Min Act: -0.1700
Data Index: 7741094 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6481. Min Range: -7.6481
Max Act: 6.9606. Min Act: -0.1700
Data Index: 6895522 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6481. Min Range: -7.6481
Max Act: 6.8981. Min Act: -0.1700
Data Index: 1500931 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6481. Min Range: -7.6481
Max Act: 6.8981. Min Act: -0.1700
Data Index: 3347923 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6481. Min Range: -7.6481
Max Act: 6.8981. Min Act: -0.1700
Data Index: 944624 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6481. Min Range: -7.6481
Max Act: 6.8356. Min Act: -0.1700
Data Index: 2775193 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6481. Min Range: -7.6481
Max Act: 6.8669. Min Act: -0.1700
Data Index: 99207 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6481. Min Range: -7.6481
Max Act: 6.8669. Min Act: -0.1700
Data Index: 7780254 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6481. Min Range: -7.6481
Max Act: 6.8669. Min Act: -0.1700
Data Index: 2023690 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6481. Min Range: -7.6481
Max Act: 6.8044. Min Act: -0.1700
Data Index: 6895520 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6481. Min Range: -7.6481
Max Act: 6.8356. Min Act: -0.1700
Data Index: 6030351 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19