Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1218 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.2277. Min Act: -0.1700
Data Index: 6924015 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.2277. Min Act: -0.1700
Data Index: 6409915 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1652. Min Act: -0.1700
Data Index: 6772298 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1339. Min Act: -0.1700
Data Index: 6577838 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1339. Min Act: -0.1700
Data Index: 4600470 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1652. Min Act: -0.1700
Data Index: 2683430 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1027. Min Act: -0.1700
Data Index: 6977669 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0714. Min Act: -0.1700
Data Index: 2118177 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0870. Min Act: -0.1700
Data Index: 7067852 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0558. Min Act: -0.1700
Data Index: 7067856 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0714. Min Act: -0.1700
Data Index: 6195743 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0558. Min Act: -0.1700
Data Index: 3543936 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0558. Min Act: -0.1700
Data Index: 914805 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0402. Min Act: -0.1700
Data Index: 1281743 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0245. Min Act: -0.1700
Data Index: 7552624 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0245. Min Act: -0.1700
Data Index: 7405251 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0245. Min Act: -0.1700
Data Index: 5731071 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0089. Min Act: -0.1700
Data Index: 6215119 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0089. Min Act: -0.1700
Data Index: 8821552 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.9933. Min Act: -0.1700
Data Index: 5431722 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19