Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1404 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3018. Min Range: -6.3018
Max Act: 6.3018. Min Act: -0.1700
Data Index: 8321358 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3018. Min Range: -6.3018
Max Act: 6.2393. Min Act: -0.1700
Data Index: 8236644 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.8956. Min Act: -0.1700
Data Index: 8800120 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.8018. Min Act: -0.1700
Data Index: 3231197 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.8018. Min Act: -0.1700
Data Index: 6729040 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.7706. Min Act: -0.1700
Data Index: 7081948 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.7393. Min Act: -0.1700
Data Index: 659470 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.6768. Min Act: -0.1700
Data Index: 2459343 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.7081. Min Act: -0.1700
Data Index: 8642796 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.7081. Min Act: -0.1700
Data Index: 3231196 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.6768. Min Act: -0.1700
Data Index: 4970221 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.6768. Min Act: -0.1700
Data Index: 3112179 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.6768. Min Act: -0.1700
Data Index: 2317920 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.6456. Min Act: -0.1700
Data Index: 8653685 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.6143. Min Act: -0.1700
Data Index: 5541434 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.6456. Min Act: -0.1700
Data Index: 4552048 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.6143. Min Act: -0.1700
Data Index: 7976943 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.6143. Min Act: -0.1700
Data Index: 6990429 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.6143. Min Act: -0.1700
Data Index: 4561739 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3018. Min Range: -6.3018
Max Act: 5.5518. Min Act: -0.1700
Data Index: 8112422 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19