Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4296 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2086. Min Range: -8.2086
Max Act: 8.2086. Min Act: -0.1700
Data Index: 3301083 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2086. Min Range: -8.2086
Max Act: 8.0211. Min Act: -0.1700
Data Index: 7962970 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.9586. Min Act: -0.1700
Data Index: 1541867 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.9586. Min Act: -0.1700
Data Index: 8599479 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.8961. Min Act: -0.1700
Data Index: 3771550 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.8961. Min Act: -0.1700
Data Index: 8590801 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.8961. Min Act: -0.1700
Data Index: 4233843 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.8336. Min Act: -0.1700
Data Index: 8590789 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.8336. Min Act: -0.1700
Data Index: 4569981 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.7711. Min Act: -0.1700
Data Index: 6679383 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.7711. Min Act: -0.1700
Data Index: 619723 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.7711. Min Act: -0.1700
Data Index: 8590790 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.7711. Min Act: -0.1700
Data Index: 7907446 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.8336. Min Act: -0.1700
Data Index: 4912266 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.7711. Min Act: -0.1700
Data Index: 3128872 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.6461. Min Act: -0.1700
Data Index: 6225632 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.6461. Min Act: -0.1700
Data Index: 3694037 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.6461. Min Act: -0.1700
Data Index: 2673132 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.6461. Min Act: -0.1700
Data Index: 2962000 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2086. Min Range: -8.2086
Max Act: 7.6461. Min Act: -0.1700
Data Index: 7234644 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19