Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2651 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.8487. Min Act: -0.1700
Data Index: 564572 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.8174. Min Act: -0.1700
Data Index: 2909709 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.6924. Min Act: -0.1700
Data Index: 3387000 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.5987. Min Act: -0.1700
Data Index: 5481838 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.5674. Min Act: -0.1700
Data Index: 5670229 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.5049. Min Act: -0.1700
Data Index: 5583871 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.5362. Min Act: -0.1700
Data Index: 244938 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.5049. Min Act: -0.1700
Data Index: 2576399 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.5049. Min Act: -0.1700
Data Index: 4609201 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.4737. Min Act: -0.1700
Data Index: 1155165 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.4737. Min Act: -0.1700
Data Index: 7250135 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.4737. Min Act: -0.1700
Data Index: 8809049 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.4737. Min Act: -0.1700
Data Index: 7405204 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.5049. Min Act: -0.1700
Data Index: 439892 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.4424. Min Act: -0.1700
Data Index: 5437937 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.4424. Min Act: -0.1700
Data Index: 668141 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.4424. Min Act: -0.1700
Data Index: 1587377 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.4111. Min Act: -0.1700
Data Index: 3990972 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.4111. Min Act: -0.1700
Data Index: 2603622 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8487. Min Range: -4.8487
Max Act: 4.4111. Min Act: -0.1700
Data Index: 4245728 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19