Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5493 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.7333. Min Act: -0.1700
Data Index: 137489 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.7020. Min Act: -0.1700
Data Index: 6941340 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.6395. Min Act: -0.1700
Data Index: 6350612 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.6083. Min Act: -0.1700
Data Index: 7058403 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.6083. Min Act: -0.1700
Data Index: 3166603 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.6083. Min Act: -0.1700
Data Index: 568256 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.5770. Min Act: -0.1700
Data Index: 2285887 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.5770. Min Act: -0.1700
Data Index: 2192623 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.5458. Min Act: -0.1700
Data Index: 151261 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.5458. Min Act: -0.1700
Data Index: 2157114 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.5458. Min Act: -0.1700
Data Index: 1608032 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.5145. Min Act: -0.1700
Data Index: 1977389 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.4833. Min Act: -0.1700
Data Index: 6976113 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.4520. Min Act: -0.1700
Data Index: 3704602 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.4520. Min Act: -0.1700
Data Index: 631868 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.4833. Min Act: -0.1700
Data Index: 360794 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.4520. Min Act: -0.1700
Data Index: 4055820 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.4520. Min Act: -0.1700
Data Index: 3431623 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.4208. Min Act: -0.1700
Data Index: 3513301 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7333. Min Range: -4.7333
Max Act: 4.4208. Min Act: -0.1700
Data Index: 8034051 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19