Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2949 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4422. Min Range: -7.4422
Max Act: 7.4422. Min Act: -0.1700
Data Index: 4596826 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4422. Min Range: -7.4422
Max Act: 7.3172. Min Act: -0.1700
Data Index: 5633684 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4422. Min Range: -7.4422
Max Act: 7.2235. Min Act: -0.1700
Data Index: 4549608 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4422. Min Range: -7.4422
Max Act: 7.2235. Min Act: -0.1700
Data Index: 87659 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4422. Min Range: -7.4422
Max Act: 7.0985. Min Act: -0.1700
Data Index: 2577654 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4422. Min Range: -7.4422
Max Act: 7.0360. Min Act: -0.1700
Data Index: 7111387 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4422. Min Range: -7.4422
Max Act: 7.0047. Min Act: -0.1700
Data Index: 5138298 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4422. Min Range: -7.4422
Max Act: 6.9735. Min Act: -0.1700
Data Index: 5613170 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4422. Min Range: -7.4422
Max Act: 6.9422. Min Act: -0.1700
Data Index: 5335531 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4422. Min Range: -7.4422
Max Act: 6.9422. Min Act: -0.1700
Data Index: 3980285 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4422. Min Range: -7.4422
Max Act: 6.9110. Min Act: -0.1700
Data Index: 6919623 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4422. Min Range: -7.4422
Max Act: 6.9110. Min Act: -0.1700
Data Index: 6137412 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4422. Min Range: -7.4422
Max Act: 6.8797. Min Act: -0.1700
Data Index: 8344978 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4422. Min Range: -7.4422
Max Act: 6.8485. Min Act: -0.1700
Data Index: 3855341 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4422. Min Range: -7.4422
Max Act: 6.8485. Min Act: -0.1700
Data Index: 6841088 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4422. Min Range: -7.4422
Max Act: 6.8172. Min Act: -0.1700
Data Index: 395466 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4422. Min Range: -7.4422
Max Act: 6.7235. Min Act: -0.1700
Data Index: 3261113 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4422. Min Range: -7.4422
Max Act: 6.7235. Min Act: -0.1700
Data Index: 419414 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4422. Min Range: -7.4422
Max Act: 6.7547. Min Act: -0.1700
Data Index: 2028935 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4422. Min Range: -7.4422
Max Act: 6.7547. Min Act: -0.1700
Data Index: 945237 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19