Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 445 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.6461. Min Act: -0.1700
Data Index: 2944425 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.5211. Min Act: -0.1700
Data Index: 7913785 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.4898. Min Act: -0.1700
Data Index: 949990 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3961. Min Act: -0.1700
Data Index: 1999638 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3961. Min Act: -0.1700
Data Index: 3599451 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3648. Min Act: -0.1700
Data Index: 4420055 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3336. Min Act: -0.1700
Data Index: 8110626 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3336. Min Act: -0.1700
Data Index: 5973489 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3336. Min Act: -0.1700
Data Index: 2337777 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3336. Min Act: -0.1700
Data Index: 2167420 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3023. Min Act: -0.1700
Data Index: 4059018 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.2711. Min Act: -0.1700
Data Index: 6637094 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3336. Min Act: -0.1700
Data Index: 6477542 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3023. Min Act: -0.1700
Data Index: 841042 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3023. Min Act: -0.1700
Data Index: 7247057 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3023. Min Act: -0.1700
Data Index: 4472218 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3023. Min Act: -0.1700
Data Index: 4941736 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.2711. Min Act: -0.1700
Data Index: 2799830 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3023. Min Act: -0.1700
Data Index: 5547258 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6461. Min Range: -4.6461
Max Act: 4.3023. Min Act: -0.1700
Data Index: 6436822 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19