Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5066 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3160. Min Range: -6.3160
Max Act: 6.3160. Min Act: -0.1700
Data Index: 448892 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3160. Min Range: -6.3160
Max Act: 6.2848. Min Act: -0.1700
Data Index: 4668290 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3160. Min Range: -6.3160
Max Act: 6.2535. Min Act: -0.1700
Data Index: 7419948 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3160. Min Range: -6.3160
Max Act: 6.1910. Min Act: -0.1700
Data Index: 3643464 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3160. Min Range: -6.3160
Max Act: 6.1598. Min Act: -0.1700
Data Index: 2983592 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3160. Min Range: -6.3160
Max Act: 6.1598. Min Act: -0.1700
Data Index: 7060329 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3160. Min Range: -6.3160
Max Act: 6.0973. Min Act: -0.1700
Data Index: 6026176 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3160. Min Range: -6.3160
Max Act: 6.0660. Min Act: -0.1700
Data Index: 2482074 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3160. Min Range: -6.3160
Max Act: 6.0973. Min Act: -0.1700
Data Index: 1003854 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3160. Min Range: -6.3160
Max Act: 6.0660. Min Act: -0.1700
Data Index: 3786092 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3160. Min Range: -6.3160
Max Act: 6.0660. Min Act: -0.1700
Data Index: 3961270 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3160. Min Range: -6.3160
Max Act: 6.0035. Min Act: -0.1700
Data Index: 993439 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3160. Min Range: -6.3160
Max Act: 6.0035. Min Act: -0.1700
Data Index: 4011932 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3160. Min Range: -6.3160
Max Act: 5.9723. Min Act: -0.1700
Data Index: 3660260 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3160. Min Range: -6.3160
Max Act: 5.9723. Min Act: -0.1700
Data Index: 4668577 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3160. Min Range: -6.3160
Max Act: 5.9723. Min Act: -0.1700
Data Index: 4633470 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3160. Min Range: -6.3160
Max Act: 5.9723. Min Act: -0.1700
Data Index: 4416234 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3160. Min Range: -6.3160
Max Act: 5.9723. Min Act: -0.1700
Data Index: 3411059 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3160. Min Range: -6.3160
Max Act: 5.9098. Min Act: -0.1700
Data Index: 6619797 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3160. Min Range: -6.3160
Max Act: 5.8785. Min Act: -0.1700
Data Index: 2327615 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19