Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3759 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.3319. Min Act: -0.1700
Data Index: 2255811 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.3319. Min Act: -0.1700
Data Index: 3641484 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.2825. Min Act: -0.1700
Data Index: 256450 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.2990. Min Act: -0.1700
Data Index: 2421547 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.2661. Min Act: -0.1700
Data Index: 2976526 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.2661. Min Act: -0.1700
Data Index: 261763 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.2495. Min Act: -0.1700
Data Index: 927408 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.2495. Min Act: -0.1700
Data Index: 4861611 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.2330. Min Act: -0.1700
Data Index: 6249232 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.1833. Min Act: -0.1700
Data Index: 3398791 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.2164. Min Act: -0.1700
Data Index: 39489 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.1833. Min Act: -0.1700
Data Index: 305361 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.1666. Min Act: -0.1700
Data Index: 837442 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.1999. Min Act: -0.1700
Data Index: 604789 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.1999. Min Act: -0.1700
Data Index: 2700969 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.1666. Min Act: -0.1700
Data Index: 6101809 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.2164. Min Act: -0.1700
Data Index: 6365811 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.1999. Min Act: -0.1700
Data Index: 7876523 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.1833. Min Act: -0.1700
Data Index: 3132844 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3319. Min Range: -2.3319
Max Act: 2.1500. Min Act: -0.1700
Data Index: 4008312 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19