Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3729 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2168. Min Range: -5.2168
Max Act: 5.2168. Min Act: -0.1700
Data Index: 4814089 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2168. Min Range: -5.2168
Max Act: 5.0918. Min Act: -0.1700
Data Index: 7038193 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2168. Min Range: -5.2168
Max Act: 5.0918. Min Act: -0.1700
Data Index: 6018420 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2168. Min Range: -5.2168
Max Act: 5.0918. Min Act: -0.1700
Data Index: 1321144 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2168. Min Range: -5.2168
Max Act: 5.0293. Min Act: -0.1700
Data Index: 8422272 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2168. Min Range: -5.2168
Max Act: 5.0293. Min Act: -0.1700
Data Index: 6116872 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2168. Min Range: -5.2168
Max Act: 4.9981. Min Act: -0.1700
Data Index: 5463818 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2168. Min Range: -5.2168
Max Act: 4.9981. Min Act: -0.1700
Data Index: 8230012 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2168. Min Range: -5.2168
Max Act: 4.9981. Min Act: -0.1700
Data Index: 2974543 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2168. Min Range: -5.2168
Max Act: 4.9668. Min Act: -0.1700
Data Index: 8513691 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2168. Min Range: -5.2168
Max Act: 4.9356. Min Act: -0.1700
Data Index: 3775531 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2168. Min Range: -5.2168
Max Act: 4.9356. Min Act: -0.1700
Data Index: 1631283 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2168. Min Range: -5.2168
Max Act: 4.9356. Min Act: -0.1700
Data Index: 694930 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2168. Min Range: -5.2168
Max Act: 4.9356. Min Act: -0.1700
Data Index: 3854185 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2168. Min Range: -5.2168
Max Act: 4.9043. Min Act: -0.1700
Data Index: 2575144 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2168. Min Range: -5.2168
Max Act: 4.9043. Min Act: -0.1700
Data Index: 3199619 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2168. Min Range: -5.2168
Max Act: 4.9043. Min Act: -0.1700
Data Index: 7059992 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2168. Min Range: -5.2168
Max Act: 4.8731. Min Act: -0.1700
Data Index: 2266784 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2168. Min Range: -5.2168
Max Act: 4.8731. Min Act: -0.1700
Data Index: 4958985 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2168. Min Range: -5.2168
Max Act: 4.8731. Min Act: -0.1700
Data Index: 1999470 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19