Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2880 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0317. Min Range: -7.0317
Max Act: 7.0317. Min Act: -0.1700
Data Index: 4923906 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.8442. Min Act: -0.1700
Data Index: 659619 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.8129. Min Act: -0.1700
Data Index: 5751158 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.8129. Min Act: -0.1700
Data Index: 8519488 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.7192. Min Act: -0.1700
Data Index: 5899198 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.6567. Min Act: -0.1700
Data Index: 6369726 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.5942. Min Act: -0.1700
Data Index: 5168861 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.5317. Min Act: -0.1700
Data Index: 8748190 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.5004. Min Act: -0.1700
Data Index: 7596884 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.5004. Min Act: -0.1700
Data Index: 3840943 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.3754. Min Act: -0.1700
Data Index: 6748119 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.3442. Min Act: -0.1700
Data Index: 661231 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.3754. Min Act: -0.1700
Data Index: 8661531 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.3754. Min Act: -0.1700
Data Index: 4251038 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.3442. Min Act: -0.1700
Data Index: 146690 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.3442. Min Act: -0.1700
Data Index: 8265356 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.2817. Min Act: -0.1700
Data Index: 7713012 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.2817. Min Act: -0.1700
Data Index: 2617060 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.2504. Min Act: -0.1700
Data Index: 3347480 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.2192. Min Act: -0.1700
Data Index: 3325588 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19