Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2337 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.4391. Min Act: -0.1700
Data Index: 6587333 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.4234. Min Act: -0.1700
Data Index: 399245 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.4704. Min Act: -0.1700
Data Index: 6587316 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3921. Min Act: -0.1700
Data Index: 6500451 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.4077. Min Act: -0.1700
Data Index: 6508696 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.4077. Min Act: -0.1700
Data Index: 6587315 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3921. Min Act: -0.1700
Data Index: 6500437 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3921. Min Act: -0.1700
Data Index: 6587334 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3921. Min Act: -0.1700
Data Index: 6587324 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3764. Min Act: -0.1700
Data Index: 997028 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3764. Min Act: -0.1700
Data Index: 6500435 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3764. Min Act: -0.1700
Data Index: 6131863 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3764. Min Act: -0.1700
Data Index: 6131859 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3607. Min Act: -0.1700
Data Index: 6587329 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3607. Min Act: -0.1700
Data Index: 2293114 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3607. Min Act: -0.1700
Data Index: 6131869 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3764. Min Act: -0.1700
Data Index: 3505382 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3607. Min Act: -0.1700
Data Index: 6500442 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3450. Min Act: -0.1700
Data Index: 3289796 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3450. Min Act: -0.1700
Data Index: 6500439 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19