Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3214 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.4292. Min Act: -0.1700
Data Index: 120901 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.4292. Min Act: -0.1700
Data Index: 8302558 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.3980. Min Act: -0.1700
Data Index: 8034600 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.3667. Min Act: -0.1700
Data Index: 1076757 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.3355. Min Act: -0.1700
Data Index: 4939495 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.3042. Min Act: -0.1700
Data Index: 2163263 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.3042. Min Act: -0.1700
Data Index: 74777 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.2730. Min Act: -0.1700
Data Index: 6661273 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.2417. Min Act: -0.1700
Data Index: 589894 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.2105. Min Act: -0.1700
Data Index: 8179574 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.1167. Min Act: -0.1700
Data Index: 96727 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.1480. Min Act: -0.1700
Data Index: 7555739 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.1167. Min Act: -0.1700
Data Index: 423129 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.1167. Min Act: -0.1700
Data Index: 5182264 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.1167. Min Act: -0.1700
Data Index: 8303288 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.0855. Min Act: -0.1700
Data Index: 1400696 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.0855. Min Act: -0.1700
Data Index: 4993701 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.0855. Min Act: -0.1700
Data Index: 4311343 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.0855. Min Act: -0.1700
Data Index: 4825258 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4292. Min Range: -4.4292
Max Act: 4.0542. Min Act: -0.1700
Data Index: 8048849 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19