Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2462 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.5628. Min Act: -0.1700
Data Index: 2657707 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.5003. Min Act: -0.1700
Data Index: 852031 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.4378. Min Act: -0.1700
Data Index: 7997584 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.4378. Min Act: -0.1700
Data Index: 1123043 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.4378. Min Act: -0.1700
Data Index: 2295756 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.4378. Min Act: -0.1699
Data Index: 8028073 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.5003. Min Act: -0.1700
Data Index: 4376159 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.3753. Min Act: -0.1700
Data Index: 1732585 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.3753. Min Act: -0.1700
Data Index: 5641418 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.3753. Min Act: -0.1700
Data Index: 2863793 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.3128. Min Act: -0.1700
Data Index: 3276054 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.3128. Min Act: -0.1700
Data Index: 2524030 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.3128. Min Act: -0.1700
Data Index: 7831248 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.3128. Min Act: -0.1700
Data Index: 4482971 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.3128. Min Act: -0.1700
Data Index: 6488764 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.1878. Min Act: -0.1700
Data Index: 430923 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.2503. Min Act: -0.1700
Data Index: 1180497 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.2503. Min Act: -0.1700
Data Index: 362480 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.2503. Min Act: -0.1700
Data Index: 7265176 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5628. Min Range: -8.5628
Max Act: 8.1878. Min Act: -0.1700
Data Index: 2460598 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19