Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3319 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.8773. Min Act: -0.1700
Data Index: 4345529 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.8773. Min Act: -0.1700
Data Index: 8507147 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.5961. Min Act: -0.1700
Data Index: 3956774 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.4711. Min Act: -0.1700
Data Index: 5803969 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.4398. Min Act: -0.1700
Data Index: 2351821 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.4086. Min Act: -0.1700
Data Index: 6373147 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.3773. Min Act: -0.1700
Data Index: 2683202 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.4086. Min Act: -0.1700
Data Index: 6430155 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.3773. Min Act: -0.1700
Data Index: 7300424 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.4086. Min Act: -0.1700
Data Index: 8407466 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.3773. Min Act: -0.1700
Data Index: 6234006 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.3461. Min Act: -0.1700
Data Index: 3301003 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.3148. Min Act: -0.1700
Data Index: 2847767 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.3461. Min Act: -0.1700
Data Index: 2386360 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.2836. Min Act: -0.1700
Data Index: 2053827 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.3148. Min Act: -0.1700
Data Index: 2000197 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.2836. Min Act: -0.1700
Data Index: 3097004 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.2836. Min Act: -0.1700
Data Index: 6110594 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.2836. Min Act: -0.1700
Data Index: 5062762 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8773. Min Range: -5.8773
Max Act: 5.2836. Min Act: -0.1700
Data Index: 4775761 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19