Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 479 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3458. Min Range: -9.3458
Max Act: 9.3458. Min Act: -0.1700
Data Index: 7524257 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3458. Min Range: -9.3458
Max Act: 9.0958. Min Act: -0.1697
Data Index: 5837088 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.9083. Min Act: -0.1700
Data Index: 3186429 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.7208. Min Act: -0.1700
Data Index: 4434665 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.7833. Min Act: -0.1700
Data Index: 6979459 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.7208. Min Act: -0.1700
Data Index: 5595071 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.6583. Min Act: -0.1700
Data Index: 841142 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.5958. Min Act: -0.1700
Data Index: 894196 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.5958. Min Act: -0.1700
Data Index: 4460114 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.5958. Min Act: -0.1700
Data Index: 6404222 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.5333. Min Act: -0.1700
Data Index: 5150785 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.4708. Min Act: -0.1700
Data Index: 7303296 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.4708. Min Act: -0.1700
Data Index: 2004106 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.4708. Min Act: -0.1700
Data Index: 2234262 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.4708. Min Act: -0.1700
Data Index: 4385625 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.4083. Min Act: -0.1700
Data Index: 8458775 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.3458. Min Act: -0.1700
Data Index: 4812666 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.3458. Min Act: -0.1700
Data Index: 5837062 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.3458. Min Act: -0.1700
Data Index: 5334291 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3458. Min Range: -9.3458
Max Act: 8.4083. Min Act: -0.1700
Data Index: 4388913 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19