Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.9143. Min Act: -0.1700
Data Index: 742119 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.7581. Min Act: -0.1700
Data Index: 5577050 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.7268. Min Act: -0.1700
Data Index: 6039665 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.6018. Min Act: -0.1700
Data Index: 3287749 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.6018. Min Act: -0.1700
Data Index: 1067195 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.5706. Min Act: -0.1700
Data Index: 1211587 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.5393. Min Act: -0.1700
Data Index: 2179257 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.5081. Min Act: -0.1700
Data Index: 6361958 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.4456. Min Act: -0.1700
Data Index: 6725622 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.4768. Min Act: -0.1700
Data Index: 4288634 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.4456. Min Act: -0.1700
Data Index: 4706347 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.4143. Min Act: -0.1700
Data Index: 3603967 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.4456. Min Act: -0.1700
Data Index: 519145 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.3831. Min Act: -0.1700
Data Index: 4222984 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.4456. Min Act: -0.1700
Data Index: 576127 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.3518. Min Act: -0.1700
Data Index: 3842260 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.3831. Min Act: -0.1700
Data Index: 24350 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.3518. Min Act: -0.1700
Data Index: 4640355 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.3518. Min Act: -0.1700
Data Index: 5872704 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9143. Min Range: -6.9143
Max Act: 6.3518. Min Act: -0.1700
Data Index: 2655450 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19