Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4200 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.7614. Min Act: -0.1700
Data Index: 5929029 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.6989. Min Act: -0.1700
Data Index: 1385712 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.6989. Min Act: -0.1700
Data Index: 5911391 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.5426. Min Act: -0.1700
Data Index: 4471963 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.5114. Min Act: -0.1700
Data Index: 2554569 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.5114. Min Act: -0.1700
Data Index: 3212881 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.4801. Min Act: -0.1700
Data Index: 4908613 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.4489. Min Act: -0.1700
Data Index: 8491785 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.3864. Min Act: -0.1700
Data Index: 7852490 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.4176. Min Act: -0.1700
Data Index: 7283529 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.3864. Min Act: -0.1700
Data Index: 336523 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.3864. Min Act: -0.1700
Data Index: 5354097 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.3864. Min Act: -0.1700
Data Index: 8576144 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.3864. Min Act: -0.1700
Data Index: 65778 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.3864. Min Act: -0.1700
Data Index: 8647560 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.3864. Min Act: -0.1700
Data Index: 1007040 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.3551. Min Act: -0.1700
Data Index: 6482924 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.3551. Min Act: -0.1700
Data Index: 4411304 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.3239. Min Act: -0.1700
Data Index: 6361743 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7614. Min Range: -6.7614
Max Act: 6.3239. Min Act: -0.1700
Data Index: 3419100 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19