Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 287 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1413. Min Range: -9.1413
Max Act: 9.1413. Min Act: -0.1700
Data Index: 1633213 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1413. Min Range: -9.1413
Max Act: 9.0163. Min Act: -0.1700
Data Index: 7356757 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.9538. Min Act: -0.1700
Data Index: 7366323 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.9538. Min Act: -0.1700
Data Index: 7961292 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.8913. Min Act: -0.1700
Data Index: 6061136 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.8913. Min Act: -0.1700
Data Index: 1434085 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.8913. Min Act: -0.1700
Data Index: 3961524 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.8288. Min Act: -0.1700
Data Index: 3268956 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.8288. Min Act: -0.1700
Data Index: 6440225 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.8913. Min Act: -0.1700
Data Index: 3980555 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.8288. Min Act: -0.1700
Data Index: 7108103 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.7663. Min Act: -0.1700
Data Index: 6523427 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.7038. Min Act: -0.1700
Data Index: 7576547 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.7663. Min Act: -0.1700
Data Index: 5403348 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.7663. Min Act: -0.1700
Data Index: 3357767 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.7663. Min Act: -0.1700
Data Index: 3972187 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.7663. Min Act: -0.1700
Data Index: 6865352 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.7663. Min Act: -0.1700
Data Index: 4759482 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.7038. Min Act: -0.1700
Data Index: 5722850 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1413. Min Range: -9.1413
Max Act: 8.7038. Min Act: -0.1700
Data Index: 2333072 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19