Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2552 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3131. Min Range: -6.3131
Max Act: 6.3131. Min Act: -0.1700
Data Index: 1185271 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3131. Min Range: -6.3131
Max Act: 6.2506. Min Act: -0.1700
Data Index: 6582634 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3131. Min Range: -6.3131
Max Act: 6.2193. Min Act: -0.1700
Data Index: 4125819 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3131. Min Range: -6.3131
Max Act: 6.1881. Min Act: -0.1700
Data Index: 1089157 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3131. Min Range: -6.3131
Max Act: 6.1568. Min Act: -0.1700
Data Index: 3682857 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3131. Min Range: -6.3131
Max Act: 6.1568. Min Act: -0.1700
Data Index: 6218577 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3131. Min Range: -6.3131
Max Act: 6.0943. Min Act: -0.1700
Data Index: 7326046 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3131. Min Range: -6.3131
Max Act: 6.0943. Min Act: -0.1698
Data Index: 2158321 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3131. Min Range: -6.3131
Max Act: 6.0943. Min Act: -0.1700
Data Index: 7326047 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3131. Min Range: -6.3131
Max Act: 6.0318. Min Act: -0.1700
Data Index: 6582642 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3131. Min Range: -6.3131
Max Act: 6.0318. Min Act: -0.1700
Data Index: 6044688 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3131. Min Range: -6.3131
Max Act: 6.0006. Min Act: -0.1700
Data Index: 6455982 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3131. Min Range: -6.3131
Max Act: 6.0006. Min Act: -0.1700
Data Index: 8039106 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3131. Min Range: -6.3131
Max Act: 6.0006. Min Act: -0.1700
Data Index: 4020926 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3131. Min Range: -6.3131
Max Act: 5.9693. Min Act: -0.1700
Data Index: 4537282 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3131. Min Range: -6.3131
Max Act: 5.9693. Min Act: -0.1700
Data Index: 4743764 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3131. Min Range: -6.3131
Max Act: 5.9381. Min Act: -0.1700
Data Index: 5071056 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3131. Min Range: -6.3131
Max Act: 5.9381. Min Act: -0.1700
Data Index: 2034924 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3131. Min Range: -6.3131
Max Act: 5.9381. Min Act: -0.1700
Data Index: 6250985 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3131. Min Range: -6.3131
Max Act: 5.9381. Min Act: -0.1700
Data Index: 6208838 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19