Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1854 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.4020. Min Act: -0.1700
Data Index: 7933219 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.3082. Min Act: -0.1700
Data Index: 6091940 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.3082. Min Act: -0.1700
Data Index: 99782 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.2770. Min Act: -0.1700
Data Index: 7303693 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.2457. Min Act: -0.1700
Data Index: 914141 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.2457. Min Act: -0.1700
Data Index: 2264480 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.1520. Min Act: -0.1700
Data Index: 6628024 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.1520. Min Act: -0.1700
Data Index: 8054344 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.1832. Min Act: -0.1700
Data Index: 5287657 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.1520. Min Act: -0.1700
Data Index: 743314 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.0895. Min Act: -0.1700
Data Index: 2615275 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.1207. Min Act: -0.1700
Data Index: 2915319 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.1207. Min Act: -0.1700
Data Index: 649556 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.0895. Min Act: -0.1700
Data Index: 648519 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.0895. Min Act: -0.1700
Data Index: 5885807 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.0582. Min Act: -0.1700
Data Index: 2476859 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.0582. Min Act: -0.1700
Data Index: 2070843 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.0582. Min Act: -0.1700
Data Index: 1293329 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4020. Min Range: -5.4020
Max Act: 4.9957. Min Act: -0.1700
Data Index: 4117819 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4020. Min Range: -5.4020
Max Act: 5.0270. Min Act: -0.1700
Data Index: 2804376 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19