Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2911 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2297. Min Range: -6.2297
Max Act: 6.2297. Min Act: -0.1700
Data Index: 42401 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2297. Min Range: -6.2297
Max Act: 6.1047. Min Act: -0.1700
Data Index: 2409978 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2297. Min Range: -6.2297
Max Act: 6.0735. Min Act: -0.1700
Data Index: 6101249 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2297. Min Range: -6.2297
Max Act: 6.0110. Min Act: -0.1700
Data Index: 3873718 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2297. Min Range: -6.2297
Max Act: 6.0110. Min Act: -0.1700
Data Index: 7170002 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.9797. Min Act: -0.1700
Data Index: 8580618 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.9797. Min Act: -0.1700
Data Index: 7613380 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.9485. Min Act: -0.1700
Data Index: 8078146 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.9172. Min Act: -0.1700
Data Index: 258491 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.8860. Min Act: -0.1700
Data Index: 2073383 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.9172. Min Act: -0.1700
Data Index: 8798996 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.9172. Min Act: -0.1700
Data Index: 4065633 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.8547. Min Act: -0.1700
Data Index: 5375598 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.8860. Min Act: -0.1700
Data Index: 889555 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.8547. Min Act: -0.1700
Data Index: 8150594 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.8547. Min Act: -0.1700
Data Index: 1376739 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.8235. Min Act: -0.1700
Data Index: 6303158 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.7922. Min Act: -0.1700
Data Index: 670456 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.7922. Min Act: -0.1700
Data Index: 7351279 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2297. Min Range: -6.2297
Max Act: 5.8235. Min Act: -0.1700
Data Index: 5072821 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19