Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2947 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1093. Min Range: -7.1093
Max Act: 7.1093. Min Act: -0.1700
Data Index: 3788516 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.7656. Min Act: -0.1700
Data Index: 2897714 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.7656. Min Act: -0.1700
Data Index: 4586551 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.7343. Min Act: -0.1700
Data Index: 3240702 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.6093. Min Act: -0.1700
Data Index: 4273260 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.6093. Min Act: -0.1700
Data Index: 2696010 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.4843. Min Act: -0.1700
Data Index: 8279768 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.4843. Min Act: -0.1700
Data Index: 3025741 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.4218. Min Act: -0.1700
Data Index: 8680336 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.4531. Min Act: -0.1700
Data Index: 5223475 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.4218. Min Act: -0.1700
Data Index: 5999031 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.4218. Min Act: -0.1700
Data Index: 4463580 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.3906. Min Act: -0.1700
Data Index: 7350077 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.3906. Min Act: -0.1700
Data Index: 5549019 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.3906. Min Act: -0.1700
Data Index: 4688902 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.3593. Min Act: -0.1700
Data Index: 8288178 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.3281. Min Act: -0.1700
Data Index: 1411528 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.3281. Min Act: -0.1700
Data Index: 2777082 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.2968. Min Act: -0.1700
Data Index: 6497906 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1093. Min Range: -7.1093
Max Act: 6.2656. Min Act: -0.1700
Data Index: 5790363 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19