Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2622 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.9505. Min Act: -0.1700
Data Index: 2165449 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.8567. Min Act: -0.1700
Data Index: 3056191 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.8567. Min Act: -0.1700
Data Index: 5974169 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.7942. Min Act: -0.1700
Data Index: 1120886 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.7630. Min Act: -0.1700
Data Index: 8687767 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.7317. Min Act: -0.1700
Data Index: 2189375 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.7630. Min Act: -0.1700
Data Index: 5329812 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.7005. Min Act: -0.1700
Data Index: 228449 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.6692. Min Act: -0.1700
Data Index: 973507 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.7005. Min Act: -0.1700
Data Index: 7453594 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.7005. Min Act: -0.1700
Data Index: 1121209 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.6380. Min Act: -0.1700
Data Index: 1575382 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.6380. Min Act: -0.1700
Data Index: 4100085 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.6380. Min Act: -0.1700
Data Index: 2751071 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.6380. Min Act: -0.1700
Data Index: 6178298 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.6380. Min Act: -0.1700
Data Index: 7815868 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.6380. Min Act: -0.1700
Data Index: 7550528 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.6380. Min Act: -0.1700
Data Index: 2505443 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.6067. Min Act: -0.1700
Data Index: 7460760 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9505. Min Range: -5.9505
Max Act: 5.6067. Min Act: -0.1700
Data Index: 4101926 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19