Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6157 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1645. Min Range: -3.1645
Max Act: 3.1645. Min Act: -0.1700
Data Index: 5110379 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1645. Min Range: -3.1645
Max Act: 3.1173. Min Act: -0.1700
Data Index: 4745053 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1645. Min Range: -3.1645
Max Act: 3.1331. Min Act: -0.1700
Data Index: 7855423 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1645. Min Range: -3.1645
Max Act: 3.0700. Min Act: -0.1700
Data Index: 625606 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1645. Min Range: -3.1645
Max Act: 3.0385. Min Act: -0.1700
Data Index: 5686958 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1645. Min Range: -3.1645
Max Act: 3.0227. Min Act: -0.1700
Data Index: 2202057 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1645. Min Range: -3.1645
Max Act: 3.0227. Min Act: -0.1700
Data Index: 7621686 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1645. Min Range: -3.1645
Max Act: 3.0227. Min Act: -0.1700
Data Index: 783836 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1645. Min Range: -3.1645
Max Act: 3.0069. Min Act: -0.1695
Data Index: 3789039 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1645. Min Range: -3.1645
Max Act: 3.0069. Min Act: -0.1700
Data Index: 3639630 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1645. Min Range: -3.1645
Max Act: 2.9911. Min Act: -0.1700
Data Index: 1185043 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1645. Min Range: -3.1645
Max Act: 2.9753. Min Act: -0.1700
Data Index: 7911445 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1645. Min Range: -3.1645
Max Act: 2.9436. Min Act: -0.1700
Data Index: 4926163 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1645. Min Range: -3.1645
Max Act: 2.9436. Min Act: -0.1700
Data Index: 1897872 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1645. Min Range: -3.1645
Max Act: 2.9436. Min Act: -0.1700
Data Index: 7157120 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1645. Min Range: -3.1645
Max Act: 2.9436. Min Act: -0.1700
Data Index: 5203947 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1645. Min Range: -3.1645
Max Act: 2.9278. Min Act: -0.1700
Data Index: 3708577 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1645. Min Range: -3.1645
Max Act: 2.9119. Min Act: -0.1700
Data Index: 4025896 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1645. Min Range: -3.1645
Max Act: 2.9119. Min Act: -0.1700
Data Index: 5272542 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1645. Min Range: -3.1645
Max Act: 2.9119. Min Act: -0.1700
Data Index: 4451391 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19