Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3883 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.6296. Min Act: -0.1700
Data Index: 115027 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.5671. Min Act: -0.1700
Data Index: 913117 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.5358. Min Act: -0.1700
Data Index: 2233528 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.5046. Min Act: -0.1700
Data Index: 964098 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.4733. Min Act: -0.1700
Data Index: 566017 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.4733. Min Act: -0.1700
Data Index: 284083 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.4421. Min Act: -0.1700
Data Index: 5508207 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.4421. Min Act: -0.1700
Data Index: 3021602 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.3796. Min Act: -0.1700
Data Index: 5817826 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.3796. Min Act: -0.1700
Data Index: 444039 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.3483. Min Act: -0.1700
Data Index: 3991580 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.3483. Min Act: -0.1700
Data Index: 2566078 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.3171. Min Act: -0.1700
Data Index: 6002655 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.3171. Min Act: -0.1700
Data Index: 8055644 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.3171. Min Act: -0.1700
Data Index: 71260 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.3171. Min Act: -0.1700
Data Index: 8320447 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.3171. Min Act: -0.1700
Data Index: 7597802 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.2858. Min Act: -0.1700
Data Index: 7371347 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.3171. Min Act: -0.1700
Data Index: 2436919 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6296. Min Range: -5.6296
Max Act: 5.2858. Min Act: -0.1700
Data Index: 2116985 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19