Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3650 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.3629. Min Act: -0.1700
Data Index: 3089055 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.2691. Min Act: -0.1700
Data Index: 3771149 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.2066. Min Act: -0.1700
Data Index: 1821728 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.1754. Min Act: -0.1700
Data Index: 4826064 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.1754. Min Act: -0.1700
Data Index: 798178 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.1441. Min Act: -0.1700
Data Index: 6365083 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.0816. Min Act: -0.1700
Data Index: 1487995 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.1129. Min Act: -0.1700
Data Index: 4327008 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.1129. Min Act: -0.1700
Data Index: 7330319 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.0816. Min Act: -0.1700
Data Index: 1351827 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.1129. Min Act: -0.1700
Data Index: 3446625 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.0504. Min Act: -0.1700
Data Index: 3709035 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.0504. Min Act: -0.1700
Data Index: 4253247 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.0816. Min Act: -0.1700
Data Index: 2163610 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3629. Min Range: -5.3629
Max Act: 4.9879. Min Act: -0.1700
Data Index: 5171984 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.0191. Min Act: -0.1700
Data Index: 7470058 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.0191. Min Act: -0.1700
Data Index: 962613 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.0191. Min Act: -0.1700
Data Index: 6385995 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3629. Min Range: -5.3629
Max Act: 4.9879. Min Act: -0.1700
Data Index: 3776853 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3629. Min Range: -5.3629
Max Act: 5.0191. Min Act: -0.1700
Data Index: 4030426 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19