Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1933 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2952. Min Range: -5.2952
Max Act: 5.2952. Min Act: -0.1700
Data Index: 5500931 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2952. Min Range: -5.2952
Max Act: 5.0140. Min Act: -0.1700
Data Index: 5785422 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9515. Min Act: -0.1700
Data Index: 5094949 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9202. Min Act: -0.1700
Data Index: 2937609 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.8577. Min Act: -0.1700
Data Index: 7265804 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.8890. Min Act: -0.1700
Data Index: 2844913 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.8577. Min Act: -0.1700
Data Index: 6124677 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.8265. Min Act: -0.1700
Data Index: 6617131 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.8265. Min Act: -0.1700
Data Index: 2828540 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.7952. Min Act: -0.1700
Data Index: 6451362 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.7952. Min Act: -0.1700
Data Index: 447499 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.7952. Min Act: -0.1700
Data Index: 5214893 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.7640. Min Act: -0.1700
Data Index: 2901416 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.7640. Min Act: -0.1700
Data Index: 6528400 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.7640. Min Act: -0.1700
Data Index: 8054801 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.7327. Min Act: -0.1700
Data Index: 7023877 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.7327. Min Act: -0.1700
Data Index: 7193016 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.7327. Min Act: -0.1700
Data Index: 267840 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.7327. Min Act: -0.1700
Data Index: 6772731 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.7327. Min Act: -0.1700
Data Index: 3676209 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19