Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2082 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.6192. Min Act: -0.1700
Data Index: 5459072 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.4317. Min Act: -0.1700
Data Index: 8026399 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.4317. Min Act: -0.1700
Data Index: 50474 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.3692. Min Act: -0.1700
Data Index: 167192 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.3067. Min Act: -0.1700
Data Index: 2661225 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.3067. Min Act: -0.1700
Data Index: 3340524 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.2755. Min Act: -0.1700
Data Index: 804678 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.2755. Min Act: -0.1700
Data Index: 1993105 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.2442. Min Act: -0.1700
Data Index: 564205 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.2442. Min Act: -0.1700
Data Index: 2111841 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.2442. Min Act: -0.1700
Data Index: 2102145 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.2130. Min Act: -0.1700
Data Index: 7545631 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.2130. Min Act: -0.1700
Data Index: 6337551 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.2130. Min Act: -0.1700
Data Index: 1694266 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.2130. Min Act: -0.1700
Data Index: 5145494 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.2130. Min Act: -0.1700
Data Index: 8608554 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.1817. Min Act: -0.1700
Data Index: 3011701 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.1817. Min Act: -0.1700
Data Index: 1763807 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.1505. Min Act: -0.1700
Data Index: 591980 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6192. Min Range: -6.6192
Max Act: 6.1505. Min Act: -0.1700
Data Index: 627841 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19