Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 596 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.7112. Min Act: -0.1700
Data Index: 3507923 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.5506. Min Act: -0.1700
Data Index: 3720507 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.5506. Min Act: -0.1700
Data Index: 6587952 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.5506. Min Act: -0.1700
Data Index: 4235126 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.5667. Min Act: -0.1700
Data Index: 7097409 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.5344. Min Act: -0.1700
Data Index: 4287720 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.5020. Min Act: -0.1700
Data Index: 3720512 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.5020. Min Act: -0.1700
Data Index: 3207269 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.5344. Min Act: -0.1700
Data Index: 6094413 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.4696. Min Act: -0.1700
Data Index: 975961 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.4858. Min Act: -0.1700
Data Index: 8019949 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.4696. Min Act: -0.1700
Data Index: 8549893 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.4858. Min Act: -0.1700
Data Index: 813949 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.4696. Min Act: -0.1700
Data Index: 6131142 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.4696. Min Act: -0.1700
Data Index: 2423222 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.4858. Min Act: -0.1700
Data Index: 2357984 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.4534. Min Act: -0.1700
Data Index: 7991887 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.4534. Min Act: -0.1700
Data Index: 6231655 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.4371. Min Act: -0.1700
Data Index: 7982577 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7112. Min Range: -2.7112
Max Act: 2.4371. Min Act: -0.1700
Data Index: 1643897 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19