Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5345 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.8436. Min Act: -0.1700
Data Index: 8663150 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.7498. Min Act: -0.1700
Data Index: 8721950 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.6248. Min Act: -0.1700
Data Index: 772381 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.5311. Min Act: -0.1700
Data Index: 7470385 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.4998. Min Act: -0.1700
Data Index: 8534051 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.4373. Min Act: -0.1700
Data Index: 6930194 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.4061. Min Act: -0.1700
Data Index: 4586253 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.4061. Min Act: -0.1700
Data Index: 8725322 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.3436. Min Act: -0.1700
Data Index: 5705440 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.3436. Min Act: -0.1700
Data Index: 5216298 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.3436. Min Act: -0.1700
Data Index: 5766516 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.3748. Min Act: -0.1700
Data Index: 2815179 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.3123. Min Act: -0.1700
Data Index: 8119690 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.3123. Min Act: -0.1700
Data Index: 1087189 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.3123. Min Act: -0.1700
Data Index: 2251675 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.2811. Min Act: -0.1700
Data Index: 8489074 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.2498. Min Act: -0.1700
Data Index: 5235194 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.2498. Min Act: -0.1700
Data Index: 6469292 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.2186. Min Act: -0.1700
Data Index: 2812124 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8436. Min Range: -6.8436
Max Act: 6.2186. Min Act: -0.1700
Data Index: 7979915 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19