Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 348 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.6206. Min Act: -0.1700
Data Index: 1646976 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.5893. Min Act: -0.1700
Data Index: 1021728 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.5581. Min Act: -0.1700
Data Index: 6853099 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.4956. Min Act: -0.1700
Data Index: 6318477 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.4956. Min Act: -0.1700
Data Index: 8409601 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.4643. Min Act: -0.1700
Data Index: 8409599 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.4331. Min Act: -0.1700
Data Index: 4459309 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.4331. Min Act: -0.1700
Data Index: 4037113 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.3706. Min Act: -0.1700
Data Index: 5782112 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.3706. Min Act: -0.1700
Data Index: 155023 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.3706. Min Act: -0.1700
Data Index: 147277 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.4018. Min Act: -0.1700
Data Index: 8323391 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.3706. Min Act: -0.1700
Data Index: 5086328 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.3081. Min Act: -0.1700
Data Index: 639127 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.3081. Min Act: -0.1700
Data Index: 1412290 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.3081. Min Act: -0.1700
Data Index: 2260295 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.3081. Min Act: -0.1700
Data Index: 7881191 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.3081. Min Act: -0.1700
Data Index: 7310407 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.3393. Min Act: -0.1700
Data Index: 6830279 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6206. Min Range: -5.6206
Max Act: 5.2768. Min Act: -0.1700
Data Index: 3561462 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19