Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4816 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0505. Min Range: -6.0505
Max Act: 6.0505. Min Act: -0.1700
Data Index: 1698631 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0505. Min Range: -6.0505
Max Act: 6.0192. Min Act: -0.1700
Data Index: 7481591 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.9880. Min Act: -0.1700
Data Index: 1783874 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.9880. Min Act: -0.1700
Data Index: 3296104 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.9567. Min Act: -0.1700
Data Index: 160655 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.9567. Min Act: -0.1700
Data Index: 5218311 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.9567. Min Act: -0.1700
Data Index: 2482036 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.8942. Min Act: -0.1700
Data Index: 572231 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.8942. Min Act: -0.1700
Data Index: 8248994 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.8942. Min Act: -0.1700
Data Index: 5592227 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.8942. Min Act: -0.1700
Data Index: 8570476 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.8942. Min Act: -0.1700
Data Index: 4326154 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.8942. Min Act: -0.1700
Data Index: 5587607 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.8942. Min Act: -0.1700
Data Index: 8781605 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.8630. Min Act: -0.1700
Data Index: 8570474 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.8630. Min Act: -0.1700
Data Index: 3654773 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.8317. Min Act: -0.1700
Data Index: 5177224 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.8317. Min Act: -0.1700
Data Index: 4836990 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.8317. Min Act: -0.1700
Data Index: 8536642 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0505. Min Range: -6.0505
Max Act: 5.8317. Min Act: -0.1700
Data Index: 163330 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19