Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2181 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.6674. Min Act: -0.1700
Data Index: 5068179 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.6193. Min Act: -0.1700
Data Index: 7150467 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.5387. Min Act: -0.1700
Data Index: 1375048 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.4901. Min Act: -0.1700
Data Index: 6021386 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.4414. Min Act: -0.1700
Data Index: 3177940 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.4577. Min Act: -0.1700
Data Index: 286964 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.4577. Min Act: -0.1700
Data Index: 4007446 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.4414. Min Act: -0.1700
Data Index: 8672681 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.4251. Min Act: -0.1700
Data Index: 5759844 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.4088. Min Act: -0.1700
Data Index: 8337516 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.3434. Min Act: -0.1700
Data Index: 6228446 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.3106. Min Act: -0.1700
Data Index: 1993765 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.3270. Min Act: -0.1700
Data Index: 5817476 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.3106. Min Act: -0.1700
Data Index: 4737144 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.2941. Min Act: -0.1700
Data Index: 1153244 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.2941. Min Act: -0.1700
Data Index: 7404204 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.3106. Min Act: -0.1700
Data Index: 3621952 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.2777. Min Act: -0.1700
Data Index: 6562327 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.2612. Min Act: -0.1700
Data Index: 2158603 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6674. Min Range: -2.6674
Max Act: 2.2447. Min Act: -0.1700
Data Index: 4788440 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19