Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 675 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1711. Min Range: -6.1711
Max Act: 6.1711. Min Act: -0.1700
Data Index: 3454677 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1711. Min Range: -6.1711
Max Act: 6.0461. Min Act: -0.1700
Data Index: 1129394 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1711. Min Range: -6.1711
Max Act: 6.0461. Min Act: -0.1700
Data Index: 2324535 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.9836. Min Act: -0.1700
Data Index: 3081277 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.8899. Min Act: -0.1700
Data Index: 8562077 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.8586. Min Act: -0.1700
Data Index: 8383197 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.7961. Min Act: -0.1700
Data Index: 7671328 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.7961. Min Act: -0.1700
Data Index: 5480687 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.7336. Min Act: -0.1700
Data Index: 4401735 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.7336. Min Act: -0.1700
Data Index: 7770810 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.7336. Min Act: -0.1700
Data Index: 2864606 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.6711. Min Act: -0.1700
Data Index: 3719812 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.6711. Min Act: -0.1700
Data Index: 3341120 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.6711. Min Act: -0.1700
Data Index: 6039510 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.6711. Min Act: -0.1700
Data Index: 2957332 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.6086. Min Act: -0.1700
Data Index: 2735791 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.5774. Min Act: -0.1700
Data Index: 5046115 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.5774. Min Act: -0.1700
Data Index: 7550092 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.5774. Min Act: -0.1700
Data Index: 2156699 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1711. Min Range: -6.1711
Max Act: 5.5774. Min Act: -0.1700
Data Index: 7481163 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19