Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3869 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.7865. Min Act: -0.1700
Data Index: 7933913 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.7240. Min Act: -0.1700
Data Index: 6544111 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.5990. Min Act: -0.1700
Data Index: 2766741 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.5677. Min Act: -0.1700
Data Index: 5477640 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.4427. Min Act: -0.1700
Data Index: 2612117 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.3802. Min Act: -0.1700
Data Index: 3511000 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.3802. Min Act: -0.1700
Data Index: 1544521 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.3490. Min Act: -0.1700
Data Index: 6558758 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.3490. Min Act: -0.1700
Data Index: 7753952 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.3490. Min Act: -0.1700
Data Index: 6974859 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.3490. Min Act: -0.1700
Data Index: 4434243 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.3177. Min Act: -0.1700
Data Index: 4826851 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.3490. Min Act: -0.1700
Data Index: 2821296 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.3177. Min Act: -0.1700
Data Index: 5909896 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.2865. Min Act: -0.1700
Data Index: 7489583 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.2865. Min Act: -0.1700
Data Index: 6634460 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.2865. Min Act: -0.1700
Data Index: 2218082 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.2865. Min Act: -0.1700
Data Index: 8766825 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.2552. Min Act: -0.1700
Data Index: 713575 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7865. Min Range: -6.7865
Max Act: 6.2552. Min Act: -0.1700
Data Index: 3090503 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19