Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 316 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.6600. Min Act: -0.1700
Data Index: 5487227 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.6600. Min Act: -0.1700
Data Index: 2065507 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.5350. Min Act: -0.1700
Data Index: 8454113 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.5038. Min Act: -0.1700
Data Index: 6017470 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.5038. Min Act: -0.1700
Data Index: 294949 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.4413. Min Act: -0.1700
Data Index: 5598226 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.4725. Min Act: -0.1700
Data Index: 3378729 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.4413. Min Act: -0.1700
Data Index: 6435027 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.4725. Min Act: -0.1700
Data Index: 2100926 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.4100. Min Act: -0.1700
Data Index: 5472309 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.4100. Min Act: -0.1700
Data Index: 3446942 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.4100. Min Act: -0.1700
Data Index: 128690 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.3475. Min Act: -0.1700
Data Index: 1061947 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.3475. Min Act: -0.1700
Data Index: 7981489 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.3163. Min Act: -0.1700
Data Index: 3484674 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.2850. Min Act: -0.1700
Data Index: 844157 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.2850. Min Act: -0.1700
Data Index: 4169270 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.2850. Min Act: -0.1700
Data Index: 2789714 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.2850. Min Act: -0.1700
Data Index: 756652 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6600. Min Range: -6.6600
Max Act: 6.2538. Min Act: -0.1700
Data Index: 4456735 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19