Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3071 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.7119. Min Act: -0.1700
Data Index: 1641432 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.6649. Min Act: -0.1700
Data Index: 1942875 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.4457. Min Act: -0.1700
Data Index: 6744797 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.3830. Min Act: -0.1700
Data Index: 2458014 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.3360. Min Act: -0.1700
Data Index: 368494 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.3046. Min Act: -0.1700
Data Index: 3492335 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.3360. Min Act: -0.1700
Data Index: 5733224 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.2889. Min Act: -0.1700
Data Index: 3148693 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.2575. Min Act: -0.1700
Data Index: 206189 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.3046. Min Act: -0.1700
Data Index: 7726640 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.2889. Min Act: -0.1700
Data Index: 1728009 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.2418. Min Act: -0.1700
Data Index: 1233123 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.2575. Min Act: -0.1700
Data Index: 4355665 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.2732. Min Act: -0.1700
Data Index: 111448 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.2418. Min Act: -0.1700
Data Index: 7795228 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.1631. Min Act: -0.1700
Data Index: 7182161 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.2418. Min Act: -0.1700
Data Index: 6586487 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.2103. Min Act: -0.1700
Data Index: 3770062 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.1789. Min Act: -0.1700
Data Index: 450147 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7119. Min Range: -3.7119
Max Act: 3.2418. Min Act: -0.1700
Data Index: 4340251 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19