Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.8950. Min Act: -0.1700
Data Index: 4895821 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.8012. Min Act: -0.1700
Data Index: 7938517 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.7700. Min Act: -0.1700
Data Index: 5832405 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.7387. Min Act: -0.1700
Data Index: 4091611 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.7387. Min Act: -0.1700
Data Index: 3989399 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.7387. Min Act: -0.1700
Data Index: 8383970 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.7387. Min Act: -0.1700
Data Index: 1699430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.6762. Min Act: -0.1700
Data Index: 708691 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.6762. Min Act: -0.1700
Data Index: 7633232 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.6762. Min Act: -0.1700
Data Index: 3840088 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.6762. Min Act: -0.1700
Data Index: 5754233 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.6450. Min Act: -0.1700
Data Index: 8547235 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.6450. Min Act: -0.1700
Data Index: 4079000 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.6137. Min Act: -0.1700
Data Index: 6352626 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.6137. Min Act: -0.1700
Data Index: 698090 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.6137. Min Act: -0.1700
Data Index: 8158990 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.6137. Min Act: -0.1700
Data Index: 8042903 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.5825. Min Act: -0.1700
Data Index: 6387593 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.5825. Min Act: -0.1700
Data Index: 7249824 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8950. Min Range: -4.8950
Max Act: 4.5825. Min Act: -0.1700
Data Index: 4927448 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19