Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1142. Min Range: -3.1142
Max Act: 3.1142. Min Act: -0.1700
Data Index: 8816654 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1142. Min Range: -3.1142
Max Act: 3.0353. Min Act: -0.1700
Data Index: 7378080 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1142. Min Range: -3.1142
Max Act: 3.0511. Min Act: -0.1700
Data Index: 2331941 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1142. Min Range: -3.1142
Max Act: 3.0511. Min Act: -0.1700
Data Index: 48170 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1142. Min Range: -3.1142
Max Act: 3.0037. Min Act: -0.1700
Data Index: 8812746 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.9721. Min Act: -0.1700
Data Index: 562574 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.9246. Min Act: -0.1700
Data Index: 8332473 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.9246. Min Act: -0.1700
Data Index: 4481840 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.9088. Min Act: -0.1700
Data Index: 7476950 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.8929. Min Act: -0.1700
Data Index: 330912 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.8453. Min Act: -0.1700
Data Index: 4660751 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.8612. Min Act: -0.1700
Data Index: 5530733 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.8294. Min Act: -0.1700
Data Index: 7048347 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.8294. Min Act: -0.1700
Data Index: 3429677 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.8294. Min Act: -0.1700
Data Index: 4481838 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.8453. Min Act: -0.1700
Data Index: 3121134 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.8453. Min Act: -0.1700
Data Index: 2648293 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.8294. Min Act: -0.1700
Data Index: 6128670 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.8135. Min Act: -0.1700
Data Index: 2717906 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1142. Min Range: -3.1142
Max Act: 2.8135. Min Act: -0.1700
Data Index: 4808879 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19