Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 157 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6491. Min Range: -6.6491
Max Act: 6.6491. Min Act: -0.1700
Data Index: 7458724 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6491. Min Range: -6.6491
Max Act: 6.5241. Min Act: -0.1700
Data Index: 3724228 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6491. Min Range: -6.6491
Max Act: 6.5241. Min Act: -0.1700
Data Index: 955777 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6491. Min Range: -6.6491
Max Act: 6.4616. Min Act: -0.1700
Data Index: 8311135 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6491. Min Range: -6.6491
Max Act: 6.2741. Min Act: -0.1700
Data Index: 2303151 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6491. Min Range: -6.6491
Max Act: 6.2428. Min Act: -0.1700
Data Index: 2887497 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6491. Min Range: -6.6491
Max Act: 6.2116. Min Act: -0.1700
Data Index: 3082626 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6491. Min Range: -6.6491
Max Act: 6.2116. Min Act: -0.1700
Data Index: 2460296 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6491. Min Range: -6.6491
Max Act: 6.0553. Min Act: -0.1700
Data Index: 7621331 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6491. Min Range: -6.6491
Max Act: 5.9616. Min Act: -0.1700
Data Index: 7227322 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6491. Min Range: -6.6491
Max Act: 5.9616. Min Act: -0.1700
Data Index: 8150424 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6491. Min Range: -6.6491
Max Act: 5.9616. Min Act: -0.1700
Data Index: 3918146 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6491. Min Range: -6.6491
Max Act: 5.9303. Min Act: -0.1700
Data Index: 8393025 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6491. Min Range: -6.6491
Max Act: 5.9303. Min Act: -0.1700
Data Index: 8370233 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6491. Min Range: -6.6491
Max Act: 5.8678. Min Act: -0.1700
Data Index: 4618684 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6491. Min Range: -6.6491
Max Act: 5.9303. Min Act: -0.1700
Data Index: 263499 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6491. Min Range: -6.6491
Max Act: 5.8678. Min Act: -0.1700
Data Index: 6428811 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6491. Min Range: -6.6491
Max Act: 5.8366. Min Act: -0.1700
Data Index: 1556929 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6491. Min Range: -6.6491
Max Act: 5.8053. Min Act: -0.1700
Data Index: 6514451 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6491. Min Range: -6.6491
Max Act: 5.7741. Min Act: -0.1700
Data Index: 7823307 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19