Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4288. Min Range: -5.4288
Max Act: 5.4288. Min Act: -0.1700
Data Index: 129006 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4288. Min Range: -5.4288
Max Act: 5.2101. Min Act: -0.1700
Data Index: 4427622 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4288. Min Range: -5.4288
Max Act: 5.1476. Min Act: -0.1700
Data Index: 4959953 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4288. Min Range: -5.4288
Max Act: 5.0851. Min Act: -0.1700
Data Index: 2994055 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.9601. Min Act: -0.1700
Data Index: 7043595 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.9601. Min Act: -0.1700
Data Index: 901327 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.9913. Min Act: -0.1700
Data Index: 3034018 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.9288. Min Act: -0.1700
Data Index: 7924999 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.9288. Min Act: -0.1700
Data Index: 7320057 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.8976. Min Act: -0.1700
Data Index: 3711845 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.8663. Min Act: -0.1700
Data Index: 2876441 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.8976. Min Act: -0.1700
Data Index: 6394449 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.8976. Min Act: -0.1700
Data Index: 7901906 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.8663. Min Act: -0.1700
Data Index: 6002862 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.8351. Min Act: -0.1700
Data Index: 794477 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.8663. Min Act: -0.1700
Data Index: 5299925 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.8038. Min Act: -0.1700
Data Index: 4959951 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.8038. Min Act: -0.1700
Data Index: 5418465 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.8038. Min Act: -0.1700
Data Index: 3963887 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4288. Min Range: -5.4288
Max Act: 4.7726. Min Act: -0.1700
Data Index: 284880 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19