Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2182 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.9660. Min Act: -0.1700
Data Index: 7372589 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.9035. Min Act: -0.1700
Data Index: 3224292 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.8722. Min Act: -0.1700
Data Index: 7655939 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.8409. Min Act: -0.1700
Data Index: 7472230 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.8722. Min Act: -0.1700
Data Index: 2485294 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.8409. Min Act: -0.1700
Data Index: 7124221 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.8409. Min Act: -0.1700
Data Index: 1814664 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.8096. Min Act: -0.1700
Data Index: 8386678 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.8096. Min Act: -0.1700
Data Index: 344976 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.8096. Min Act: -0.1700
Data Index: 5200248 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.7784. Min Act: -0.1700
Data Index: 206758 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.7784. Min Act: -0.1700
Data Index: 5953105 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.7784. Min Act: -0.1700
Data Index: 1907583 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.7784. Min Act: -0.1700
Data Index: 4151554 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.7784. Min Act: -0.1700
Data Index: 8427706 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.7784. Min Act: -0.1700
Data Index: 2171368 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.7784. Min Act: -0.1700
Data Index: 2179421 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.7471. Min Act: -0.1700
Data Index: 2171373 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.7471. Min Act: -0.1700
Data Index: 6774221 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9660. Min Range: -3.9660
Max Act: 3.7471. Min Act: -0.1700
Data Index: 344978 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19