Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3310 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.3308. Min Act: -0.1700
Data Index: 3783623 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.2683. Min Act: -0.1700
Data Index: 4914301 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.2683. Min Act: -0.1700
Data Index: 4233975 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.2058. Min Act: -0.1700
Data Index: 1940269 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.2058. Min Act: -0.1700
Data Index: 4716069 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.1745. Min Act: -0.1700
Data Index: 3765966 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.1745. Min Act: -0.1700
Data Index: 6170014 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.1745. Min Act: -0.1700
Data Index: 3785979 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.1433. Min Act: -0.1700
Data Index: 457838 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.1433. Min Act: -0.1700
Data Index: 771034 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.1120. Min Act: -0.1700
Data Index: 5784496 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.1120. Min Act: -0.1700
Data Index: 719417 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.0808. Min Act: -0.1700
Data Index: 3130672 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.0808. Min Act: -0.1700
Data Index: 2551568 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.0808. Min Act: -0.1700
Data Index: 3846941 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.0808. Min Act: -0.1700
Data Index: 1739978 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.0808. Min Act: -0.1700
Data Index: 24625 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.0808. Min Act: -0.1700
Data Index: 5142850 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.0495. Min Act: -0.1700
Data Index: 91876 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3308. Min Range: -6.3308
Max Act: 6.0808. Min Act: -0.1700
Data Index: 2188421 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19