Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4246 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.7575. Min Act: -0.1700
Data Index: 124988 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.5387. Min Act: -0.1700
Data Index: 2304752 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.4450. Min Act: -0.1700
Data Index: 7851343 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.2887. Min Act: -0.1700
Data Index: 6690104 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.3200. Min Act: -0.1700
Data Index: 5935205 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.2887. Min Act: -0.1700
Data Index: 296720 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.2262. Min Act: -0.1700
Data Index: 6855427 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.2262. Min Act: -0.1700
Data Index: 3226535 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.2262. Min Act: -0.1700
Data Index: 8798525 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.1950. Min Act: -0.1700
Data Index: 6249293 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.1637. Min Act: -0.1700
Data Index: 7302567 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.1325. Min Act: -0.1700
Data Index: 5129570 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.1325. Min Act: -0.1700
Data Index: 4929579 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.1012. Min Act: -0.1700
Data Index: 3224582 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.0700. Min Act: -0.1700
Data Index: 683518 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7575. Min Range: -5.7575
Max Act: 5.0075. Min Act: -0.1700
Data Index: 2591520 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7575. Min Range: -5.7575
Max Act: 4.9762. Min Act: -0.1700
Data Index: 904672 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7575. Min Range: -5.7575
Max Act: 4.9762. Min Act: -0.1700
Data Index: 5268284 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7575. Min Range: -5.7575
Max Act: 4.9762. Min Act: -0.1700
Data Index: 8679352 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7575. Min Range: -5.7575
Max Act: 4.9762. Min Act: -0.1700
Data Index: 2525137 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19