Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2547. Min Range: -6.2547
Max Act: 6.2547. Min Act: -0.1700
Data Index: 3124508 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.9735. Min Act: -0.1700
Data Index: 7548020 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.9110. Min Act: -0.1700
Data Index: 2572684 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.9110. Min Act: -0.1700
Data Index: 5638376 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.8485. Min Act: -0.1700
Data Index: 786908 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.8485. Min Act: -0.1700
Data Index: 3632270 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.8485. Min Act: -0.1700
Data Index: 3761491 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.8485. Min Act: -0.1700
Data Index: 1961969 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.8485. Min Act: -0.1700
Data Index: 2297388 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.8172. Min Act: -0.1700
Data Index: 7106305 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.8172. Min Act: -0.1700
Data Index: 5788511 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.8172. Min Act: -0.1700
Data Index: 7450316 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.7860. Min Act: -0.1700
Data Index: 4875966 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.7547. Min Act: -0.1700
Data Index: 1941952 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.7860. Min Act: -0.1700
Data Index: 5480751 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.7860. Min Act: -0.1700
Data Index: 4058391 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.7547. Min Act: -0.1700
Data Index: 6687403 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.7547. Min Act: -0.1700
Data Index: 905940 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.7547. Min Act: -0.1700
Data Index: 427761 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2547. Min Range: -6.2547
Max Act: 5.7547. Min Act: -0.1700
Data Index: 5788512 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19