Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4199 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5864. Min Range: -7.5864
Max Act: 7.5864. Min Act: -0.1700
Data Index: 1623137 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.8364. Min Act: -0.1700
Data Index: 3973505 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.6489. Min Act: -0.1700
Data Index: 6436381 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.5864. Min Act: -0.1700
Data Index: 6144832 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.5552. Min Act: -0.1700
Data Index: 2986472 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.5239. Min Act: -0.1700
Data Index: 1318276 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.5239. Min Act: -0.1700
Data Index: 7267837 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.5239. Min Act: -0.1700
Data Index: 1975469 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.5239. Min Act: -0.1700
Data Index: 6421125 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.4927. Min Act: -0.1700
Data Index: 1335749 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.4302. Min Act: -0.1700
Data Index: 8066849 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.4302. Min Act: -0.1700
Data Index: 8312210 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.3989. Min Act: -0.1700
Data Index: 5943456 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.3989. Min Act: -0.1700
Data Index: 806109 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.3989. Min Act: -0.1700
Data Index: 3590696 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.3677. Min Act: -0.1700
Data Index: 2664128 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.3677. Min Act: -0.1700
Data Index: 3304570 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.3364. Min Act: -0.1700
Data Index: 2109024 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.3364. Min Act: -0.1700
Data Index: 219255 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5864. Min Range: -7.5864
Max Act: 6.2739. Min Act: -0.1700
Data Index: 1412676 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19