Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1792 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.8987. Min Act: -0.1700
Data Index: 4500798 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.7737. Min Act: -0.1700
Data Index: 5050975 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.6487. Min Act: -0.1700
Data Index: 7013231 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.6174. Min Act: -0.1700
Data Index: 7459337 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.6174. Min Act: -0.1700
Data Index: 468942 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.5549. Min Act: -0.1700
Data Index: 4725361 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.5237. Min Act: -0.1700
Data Index: 797528 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.4924. Min Act: -0.1700
Data Index: 130397 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.4924. Min Act: -0.1700
Data Index: 104566 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.5237. Min Act: -0.1700
Data Index: 8496599 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.4924. Min Act: -0.1700
Data Index: 8828956 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.4612. Min Act: -0.1700
Data Index: 4985969 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.4612. Min Act: -0.1700
Data Index: 3008186 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.4612. Min Act: -0.1700
Data Index: 5906005 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.3987. Min Act: -0.1700
Data Index: 6895709 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.3987. Min Act: -0.1700
Data Index: 1858517 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.3674. Min Act: -0.1700
Data Index: 3248428 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.3674. Min Act: -0.1700
Data Index: 196148 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.3049. Min Act: -0.1700
Data Index: 3678172 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8987. Min Range: -7.8987
Max Act: 7.3049. Min Act: -0.1700
Data Index: 8133957 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19