Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5302 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4587. Min Range: -9.4587
Max Act: 9.4587. Min Act: -0.1700
Data Index: 8774845 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4587. Min Range: -9.4587
Max Act: 9.1462. Min Act: -0.1700
Data Index: 4909380 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.9587. Min Act: -0.1700
Data Index: 3433039 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.9587. Min Act: -0.1700
Data Index: 7205856 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.8337. Min Act: -0.1700
Data Index: 6966264 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.8337. Min Act: -0.1700
Data Index: 5204671 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.7712. Min Act: -0.1699
Data Index: 4279508 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.7712. Min Act: -0.1700
Data Index: 1604133 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.7087. Min Act: -0.1700
Data Index: 7149067 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.7087. Min Act: -0.1700
Data Index: 1495274 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.7087. Min Act: -0.1700
Data Index: 2560257 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.6462. Min Act: -0.1700
Data Index: 4149072 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.5837. Min Act: -0.1700
Data Index: 7222703 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.5837. Min Act: -0.1700
Data Index: 6597009 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.6462. Min Act: -0.1700
Data Index: 909232 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.6462. Min Act: -0.1700
Data Index: 6760709 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.5837. Min Act: -0.1700
Data Index: 1453407 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.5837. Min Act: -0.1700
Data Index: 832597 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.5837. Min Act: -0.1700
Data Index: 7924265 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4587. Min Range: -9.4587
Max Act: 8.5212. Min Act: -0.1700
Data Index: 2690339 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19