Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3971. Min Range: -7.3971
Max Act: 7.3971. Min Act: -0.1700
Data Index: 4399536 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.7096. Min Act: -0.1700
Data Index: 5321378 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.6159. Min Act: -0.1700
Data Index: 7051871 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.6159. Min Act: -0.1700
Data Index: 5919297 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.5534. Min Act: -0.1700
Data Index: 652852 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.4596. Min Act: -0.1700
Data Index: 3277490 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.4284. Min Act: -0.1700
Data Index: 5524520 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.3346. Min Act: -0.1700
Data Index: 5593953 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.3346. Min Act: -0.1700
Data Index: 8365234 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.3346. Min Act: -0.1700
Data Index: 5919301 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.3034. Min Act: -0.1700
Data Index: 5593958 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.3034. Min Act: -0.1700
Data Index: 5157693 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.2721. Min Act: -0.1700
Data Index: 3033713 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.2721. Min Act: -0.1700
Data Index: 1395147 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.2721. Min Act: -0.1700
Data Index: 2017422 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.2409. Min Act: -0.1700
Data Index: 3334265 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.2096. Min Act: -0.1700
Data Index: 629549 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.2096. Min Act: -0.1700
Data Index: 782196 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.1784. Min Act: -0.1700
Data Index: 4542253 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3971. Min Range: -7.3971
Max Act: 6.1784. Min Act: -0.1700
Data Index: 6884722 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19