Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.7689. Min Act: -0.1700
Data Index: 8148936 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.6439. Min Act: -0.1700
Data Index: 4101773 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.5814. Min Act: -0.1700
Data Index: 2865464 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.5502. Min Act: -0.1700
Data Index: 7438567 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.5502. Min Act: -0.1700
Data Index: 5967949 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.4564. Min Act: -0.1700
Data Index: 2424571 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.4877. Min Act: -0.1700
Data Index: 1133590 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.5189. Min Act: -0.1700
Data Index: 5967951 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.4252. Min Act: -0.1700
Data Index: 2469606 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.4252. Min Act: -0.1700
Data Index: 1414718 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.3939. Min Act: -0.1700
Data Index: 79485 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.3627. Min Act: -0.1700
Data Index: 4101774 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.3627. Min Act: -0.1700
Data Index: 3304272 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.3314. Min Act: -0.1700
Data Index: 585163 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.3002. Min Act: -0.1700
Data Index: 5116405 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.2689. Min Act: -0.1700
Data Index: 8009374 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.2689. Min Act: -0.1700
Data Index: 6843683 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.2377. Min Act: -0.1700
Data Index: 6860633 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.2377. Min Act: -0.1700
Data Index: 2634810 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7689. Min Range: -5.7689
Max Act: 5.2377. Min Act: -0.1700
Data Index: 4708999 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19