Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 223 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.4140. Min Act: -0.1700
Data Index: 1745772 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.3042. Min Act: -0.1700
Data Index: 877047 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.2885. Min Act: -0.1700
Data Index: 1731678 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.2414. Min Act: -0.1700
Data Index: 4796249 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.2099. Min Act: -0.1700
Data Index: 7796399 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.2099. Min Act: -0.1700
Data Index: 2067741 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.1942. Min Act: -0.1700
Data Index: 4778617 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.1942. Min Act: -0.1700
Data Index: 6289187 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.2257. Min Act: -0.1700
Data Index: 6335880 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.2099. Min Act: -0.1700
Data Index: 270317 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.1942. Min Act: -0.1700
Data Index: 7607910 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.1155. Min Act: -0.1700
Data Index: 1014513 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.1470. Min Act: -0.1700
Data Index: 8238385 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.1470. Min Act: -0.1700
Data Index: 7773218 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.1470. Min Act: -0.1700
Data Index: 5747476 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.1313. Min Act: -0.1700
Data Index: 4124416 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.1313. Min Act: -0.1700
Data Index: 7565699 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.1313. Min Act: -0.1700
Data Index: 6402990 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.0997. Min Act: -0.1700
Data Index: 5404972 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4140. Min Range: -3.4140
Max Act: 3.1155. Min Act: -0.1700
Data Index: 1078585 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19