Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 845 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.5163. Min Act: -0.1700
Data Index: 3103721 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.3596. Min Act: -0.1700
Data Index: 463384 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.2811. Min Act: -0.1700
Data Index: 4694284 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.2811. Min Act: -0.1700
Data Index: 3166491 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.2183. Min Act: -0.1700
Data Index: 1387803 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.2183. Min Act: -0.1700
Data Index: 5845353 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.1554. Min Act: -0.1700
Data Index: 5407165 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.1239. Min Act: -0.1700
Data Index: 1093658 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.1081. Min Act: -0.1700
Data Index: 1213539 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.0766. Min Act: -0.1700
Data Index: 4390423 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.0924. Min Act: -0.1700
Data Index: 7504591 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.0924. Min Act: -0.1700
Data Index: 8406875 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.0766. Min Act: -0.1700
Data Index: 2957513 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.0766. Min Act: -0.1700
Data Index: 3761381 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.0924. Min Act: -0.1700
Data Index: 7625610 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.0766. Min Act: -0.1700
Data Index: 4406186 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.0608. Min Act: -0.1700
Data Index: 3131963 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.0766. Min Act: -0.1700
Data Index: 7945601 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.0450. Min Act: -0.1700
Data Index: 5118305 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5163. Min Range: -3.5163
Max Act: 3.0450. Min Act: -0.1700
Data Index: 3235023 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19