Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5787 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.5470. Min Act: -0.1700
Data Index: 2012180 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.5158. Min Act: -0.1700
Data Index: 3014389 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.5158. Min Act: -0.1700
Data Index: 4231883 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.4533. Min Act: -0.1700
Data Index: 1072185 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.4220. Min Act: -0.1700
Data Index: 2674602 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.4220. Min Act: -0.1700
Data Index: 1497207 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.3908. Min Act: -0.1700
Data Index: 6611480 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.3908. Min Act: -0.1700
Data Index: 1738648 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.3283. Min Act: -0.1700
Data Index: 55286 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.3283. Min Act: -0.1700
Data Index: 8745276 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.2658. Min Act: -0.1700
Data Index: 2062972 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.2658. Min Act: -0.1700
Data Index: 566280 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.2658. Min Act: -0.1700
Data Index: 63193 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.2658. Min Act: -0.1700
Data Index: 7054075 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.2033. Min Act: -0.1700
Data Index: 602198 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.2345. Min Act: -0.1700
Data Index: 7078080 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.2345. Min Act: -0.1700
Data Index: 6879769 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.2345. Min Act: -0.1700
Data Index: 7291988 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.2345. Min Act: -0.1700
Data Index: 6388252 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5470. Min Range: -6.5470
Max Act: 6.2033. Min Act: -0.1700
Data Index: 4950445 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19