Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1147 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1812. Min Range: -5.1812
Max Act: 5.1812. Min Act: -0.1700
Data Index: 3509084 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.9624. Min Act: -0.1700
Data Index: 6489620 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.9312. Min Act: -0.1700
Data Index: 6161811 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8999. Min Act: -0.1700
Data Index: 8589063 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8999. Min Act: -0.1700
Data Index: 7542033 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8687. Min Act: -0.1700
Data Index: 5266732 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8687. Min Act: -0.1700
Data Index: 8720507 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8062. Min Act: -0.1700
Data Index: 7420131 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8374. Min Act: -0.1700
Data Index: 5309454 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8374. Min Act: -0.1700
Data Index: 1164938 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8374. Min Act: -0.1700
Data Index: 2894186 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8062. Min Act: -0.1700
Data Index: 2716575 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8062. Min Act: -0.1700
Data Index: 4470567 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8062. Min Act: -0.1700
Data Index: 1516812 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.7749. Min Act: -0.1700
Data Index: 3289031 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.7749. Min Act: -0.1700
Data Index: 7023520 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.7749. Min Act: -0.1700
Data Index: 2133703 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.7437. Min Act: -0.1700
Data Index: 1510253 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.7437. Min Act: -0.1700
Data Index: 6065283 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.7437. Min Act: -0.1700
Data Index: 6802823 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19