Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4474 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.8823. Min Act: -0.1700
Data Index: 274174 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.6323. Min Act: -0.1700
Data Index: 7570705 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.6948. Min Act: -0.1700
Data Index: 4184502 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.5698. Min Act: -0.1700
Data Index: 3423640 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.5073. Min Act: -0.1700
Data Index: 8411766 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.4761. Min Act: -0.1700
Data Index: 652168 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.4761. Min Act: -0.1700
Data Index: 2167653 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.4448. Min Act: -0.1700
Data Index: 4128510 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.4136. Min Act: -0.1700
Data Index: 5040340 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.4136. Min Act: -0.1700
Data Index: 2278351 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.4136. Min Act: -0.1700
Data Index: 2668134 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.3823. Min Act: -0.1700
Data Index: 7272364 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.3823. Min Act: -0.1700
Data Index: 3599164 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.3823. Min Act: -0.1700
Data Index: 8469485 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.3511. Min Act: -0.1700
Data Index: 830452 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.3511. Min Act: -0.1700
Data Index: 5188885 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.3511. Min Act: -0.1700
Data Index: 6061390 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.3198. Min Act: -0.1700
Data Index: 3339625 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.3198. Min Act: -0.1700
Data Index: 4960954 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8823. Min Range: -5.8823
Max Act: 5.3198. Min Act: -0.1700
Data Index: 3903630 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19