Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3375 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2385. Min Range: -8.2385
Max Act: 8.2385. Min Act: -0.1700
Data Index: 1215112 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2385. Min Range: -8.2385
Max Act: 8.1135. Min Act: -0.1700
Data Index: 7454168 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2385. Min Range: -8.2385
Max Act: 8.1135. Min Act: -0.1700
Data Index: 2956892 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2385. Min Range: -8.2385
Max Act: 8.1135. Min Act: -0.1700
Data Index: 6823652 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2385. Min Range: -8.2385
Max Act: 8.0510. Min Act: -0.1700
Data Index: 4209837 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.9885. Min Act: -0.1700
Data Index: 7749523 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.9885. Min Act: -0.1700
Data Index: 6539662 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.9885. Min Act: -0.1700
Data Index: 8355164 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.9885. Min Act: -0.1700
Data Index: 4839970 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.9885. Min Act: -0.1700
Data Index: 2104022 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.9260. Min Act: -0.1700
Data Index: 5012422 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.8635. Min Act: -0.1700
Data Index: 4481260 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.8635. Min Act: -0.1700
Data Index: 4059871 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.8635. Min Act: -0.1700
Data Index: 3965855 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.8635. Min Act: -0.1700
Data Index: 6578227 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.8010. Min Act: -0.1700
Data Index: 2864964 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.8010. Min Act: -0.1700
Data Index: 5303237 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.7385. Min Act: -0.1700
Data Index: 909138 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.8635. Min Act: -0.1700
Data Index: 7009735 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.8010. Min Act: -0.1700
Data Index: 2717125 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19