Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2842 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1658. Min Range: -5.1658
Max Act: 5.1658. Min Act: -0.1700
Data Index: 8490428 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.9470. Min Act: -0.1700
Data Index: 3978694 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.9158. Min Act: -0.1700
Data Index: 1730037 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.8845. Min Act: -0.1700
Data Index: 6977830 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.8533. Min Act: -0.1700
Data Index: 2845497 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.7595. Min Act: -0.1700
Data Index: 1368956 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.7908. Min Act: -0.1700
Data Index: 1554296 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.7283. Min Act: -0.1700
Data Index: 6639421 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.7283. Min Act: -0.1700
Data Index: 8046605 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.6970. Min Act: -0.1700
Data Index: 1390785 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.6970. Min Act: -0.1700
Data Index: 6366249 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.6970. Min Act: -0.1700
Data Index: 1591506 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.6970. Min Act: -0.1700
Data Index: 491864 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.6970. Min Act: -0.1700
Data Index: 93164 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.6970. Min Act: -0.1700
Data Index: 759827 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.6345. Min Act: -0.1700
Data Index: 2041123 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.6970. Min Act: -0.1700
Data Index: 3171568 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.6658. Min Act: -0.1700
Data Index: 4626623 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.6658. Min Act: -0.1700
Data Index: 2001926 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1658. Min Range: -5.1658
Max Act: 4.6345. Min Act: -0.1700
Data Index: 6602933 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19