Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3375 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.6154. Min Act: -0.1700
Data Index: 8580434 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.5217. Min Act: -0.1700
Data Index: 2367081 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.3654. Min Act: -0.1700
Data Index: 5437690 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.2092. Min Act: -0.1700
Data Index: 7455413 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.1779. Min Act: -0.1700
Data Index: 7485089 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.1467. Min Act: -0.1700
Data Index: 4092827 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.1154. Min Act: -0.1700
Data Index: 2238258 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.0842. Min Act: -0.1700
Data Index: 7722429 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.0529. Min Act: -0.1700
Data Index: 591333 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.0529. Min Act: -0.1700
Data Index: 4071199 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.0217. Min Act: -0.1700
Data Index: 1563590 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.0217. Min Act: -0.1700
Data Index: 8251723 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.9904. Min Act: -0.1700
Data Index: 5070475 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.9904. Min Act: -0.1700
Data Index: 942226 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.9904. Min Act: -0.1700
Data Index: 7892418 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.9904. Min Act: -0.1700
Data Index: 7888423 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.0217. Min Act: -0.1700
Data Index: 2539755 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.9592. Min Act: -0.1700
Data Index: 4200490 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.9592. Min Act: -0.1700
Data Index: 5028443 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.9904. Min Act: -0.1700
Data Index: 937452 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19