Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2086 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7951. Min Range: -6.7951
Max Act: 6.7951. Min Act: -0.1700
Data Index: 150072 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7951. Min Range: -6.7951
Max Act: 6.4513. Min Act: -0.1700
Data Index: 7956449 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7951. Min Range: -6.7951
Max Act: 6.0451. Min Act: -0.1700
Data Index: 23275 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7951. Min Range: -6.7951
Max Act: 6.0138. Min Act: -0.1700
Data Index: 8626993 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.9826. Min Act: -0.1700
Data Index: 3012381 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.9826. Min Act: -0.1700
Data Index: 4206009 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.9513. Min Act: -0.1700
Data Index: 611447 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.8576. Min Act: -0.1700
Data Index: 6161318 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.8576. Min Act: -0.1700
Data Index: 5436888 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.8576. Min Act: -0.1700
Data Index: 3693023 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.7951. Min Act: -0.1700
Data Index: 7628266 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.7951. Min Act: -0.1700
Data Index: 917266 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.7951. Min Act: -0.1700
Data Index: 8137039 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.7951. Min Act: -0.1700
Data Index: 3140303 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.7951. Min Act: -0.1700
Data Index: 8422873 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.7638. Min Act: -0.1700
Data Index: 4529455 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.7638. Min Act: -0.1700
Data Index: 3036247 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.7326. Min Act: -0.1700
Data Index: 615983 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.7326. Min Act: -0.1700
Data Index: 3029028 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7951. Min Range: -6.7951
Max Act: 5.7326. Min Act: -0.1700
Data Index: 5564550 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19