Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6306 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.2886. Min Act: -0.1700
Data Index: 5829634 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.2261. Min Act: -0.1700
Data Index: 764235 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.2261. Min Act: -0.1700
Data Index: 4429514 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.1949. Min Act: -0.1700
Data Index: 91239 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.2261. Min Act: -0.1700
Data Index: 3837243 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.1949. Min Act: -0.1700
Data Index: 5376777 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.1949. Min Act: -0.1700
Data Index: 3457085 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.1324. Min Act: -0.1700
Data Index: 1625454 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.1324. Min Act: -0.1700
Data Index: 7475634 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.0699. Min Act: -0.1700
Data Index: 1063267 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.0699. Min Act: -0.1700
Data Index: 1133628 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.0386. Min Act: -0.1700
Data Index: 5596730 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.0074. Min Act: -0.1700
Data Index: 7326360 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.0386. Min Act: -0.1700
Data Index: 6353769 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2886. Min Range: -6.2886
Max Act: 6.0074. Min Act: -0.1700
Data Index: 2394203 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2886. Min Range: -6.2886
Max Act: 5.9761. Min Act: -0.1700
Data Index: 7084816 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2886. Min Range: -6.2886
Max Act: 5.9449. Min Act: -0.1700
Data Index: 2469069 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2886. Min Range: -6.2886
Max Act: 5.9449. Min Act: -0.1700
Data Index: 506730 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2886. Min Range: -6.2886
Max Act: 5.9449. Min Act: -0.1700
Data Index: 733035 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2886. Min Range: -6.2886
Max Act: 5.9449. Min Act: -0.1700
Data Index: 7280722 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19