Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5459 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.5694. Min Act: -0.1700
Data Index: 4042001 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.5694. Min Act: -0.1700
Data Index: 5215543 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.5381. Min Act: -0.1700
Data Index: 6748563 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.5381. Min Act: -0.1700
Data Index: 8204567 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.5069. Min Act: -0.1700
Data Index: 5441696 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.5381. Min Act: -0.1700
Data Index: 6473060 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.5069. Min Act: -0.1700
Data Index: 7003958 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.5069. Min Act: -0.1700
Data Index: 6079137 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.4756. Min Act: -0.1700
Data Index: 4666678 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.4444. Min Act: -0.1700
Data Index: 3359836 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.3819. Min Act: -0.1700
Data Index: 3696962 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.4131. Min Act: -0.1695
Data Index: 343567 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.4131. Min Act: -0.1700
Data Index: 2174806 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.4131. Min Act: -0.1695
Data Index: 4181494 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.3819. Min Act: -0.1700
Data Index: 2970213 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.3506. Min Act: -0.1700
Data Index: 4349547 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.3506. Min Act: -0.1700
Data Index: 948853 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.3506. Min Act: -0.1700
Data Index: 3666127 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.3819. Min Act: -0.1700
Data Index: 2112727 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5694. Min Range: -6.5694
Max Act: 6.3506. Min Act: -0.1700
Data Index: 4138156 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19