Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1859 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.7096. Min Act: -0.1700
Data Index: 2555580 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.4596. Min Act: -0.1700
Data Index: 6599230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.4596. Min Act: -0.1700
Data Index: 6354885 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.4596. Min Act: -0.1700
Data Index: 2075755 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.3658. Min Act: -0.1700
Data Index: 8589577 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.3971. Min Act: -0.1700
Data Index: 4623278 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.3658. Min Act: -0.1700
Data Index: 8240864 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.3658. Min Act: -0.1700
Data Index: 5335618 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.3658. Min Act: -0.1700
Data Index: 5440620 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.3971. Min Act: -0.1700
Data Index: 877694 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.3658. Min Act: -0.1700
Data Index: 5342459 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.3971. Min Act: -0.1700
Data Index: 4358591 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.3658. Min Act: -0.1700
Data Index: 390846 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.3346. Min Act: -0.1700
Data Index: 440473 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.2721. Min Act: -0.1700
Data Index: 8618611 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.3033. Min Act: -0.1700
Data Index: 987258 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.3033. Min Act: -0.1700
Data Index: 1806360 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.3033. Min Act: -0.1700
Data Index: 98507 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.2721. Min Act: -0.1700
Data Index: 6428583 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7096. Min Range: -4.7096
Max Act: 4.2721. Min Act: -0.1700
Data Index: 1010949 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19