Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.3129. Min Act: -0.1700
Data Index: 1320016 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.3443. Min Act: -0.1700
Data Index: 3890996 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.2658. Min Act: -0.1700
Data Index: 5783173 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.2658. Min Act: -0.1700
Data Index: 6434592 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.2815. Min Act: -0.1700
Data Index: 5591039 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.2501. Min Act: -0.1700
Data Index: 2284048 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.2344. Min Act: -0.1700
Data Index: 3794356 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.2187. Min Act: -0.1700
Data Index: 7147466 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.2029. Min Act: -0.1700
Data Index: 7553289 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.2187. Min Act: -0.1700
Data Index: 2916410 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.2029. Min Act: -0.1700
Data Index: 5841898 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.2029. Min Act: -0.1700
Data Index: 2565746 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.1872. Min Act: -0.1700
Data Index: 1515422 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.1872. Min Act: -0.1700
Data Index: 3965348 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.1715. Min Act: -0.1700
Data Index: 7013363 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.1872. Min Act: -0.1700
Data Index: 4875779 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.1557. Min Act: -0.1700
Data Index: 5538257 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.1400. Min Act: -0.1700
Data Index: 3721681 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.1557. Min Act: -0.1700
Data Index: 2946445 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3443. Min Range: -3.3443
Max Act: 3.1715. Min Act: -0.1700
Data Index: 2584873 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19