Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7568. Min Range: -10.7568
Max Act: 10.7568. Min Act: -0.1700
Data Index: 4406714 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7568. Min Range: -10.7568
Max Act: 10.6318. Min Act: -0.1700
Data Index: 6562774 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7568. Min Range: -10.7568
Max Act: 10.4443. Min Act: -0.1700
Data Index: 4304583 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7568. Min Range: -10.7568
Max Act: 10.3818. Min Act: -0.1700
Data Index: 4255869 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7568. Min Range: -10.7568
Max Act: 10.3193. Min Act: -0.1700
Data Index: 1692039 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7568. Min Range: -10.7568
Max Act: 10.3193. Min Act: -0.1700
Data Index: 4310392 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7568. Min Range: -10.7568
Max Act: 10.1943. Min Act: -0.1700
Data Index: 3563734 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7568. Min Range: -10.7568
Max Act: 10.1318. Min Act: -0.1700
Data Index: 6891541 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7568. Min Range: -10.7568
Max Act: 10.1318. Min Act: -0.1700
Data Index: 2777586 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7568. Min Range: -10.7568
Max Act: 10.1318. Min Act: -0.1700
Data Index: 2172387 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7568. Min Range: -10.7568
Max Act: 10.0693. Min Act: -0.1700
Data Index: 3042456 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7568. Min Range: -10.7568
Max Act: 10.0693. Min Act: -0.1700
Data Index: 7077494 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7568. Min Range: -10.7568
Max Act: 10.0068. Min Act: -0.1700
Data Index: 4952213 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7568. Min Range: -10.7568
Max Act: 9.9443. Min Act: -0.1700
Data Index: 6467511 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7568. Min Range: -10.7568
Max Act: 9.9443. Min Act: -0.1700
Data Index: 8474607 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7568. Min Range: -10.7568
Max Act: 9.8818. Min Act: -0.1700
Data Index: 4283733 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7568. Min Range: -10.7568
Max Act: 9.9443. Min Act: -0.1700
Data Index: 5058165 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7568. Min Range: -10.7568
Max Act: 9.9443. Min Act: -0.1700
Data Index: 7629438 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7568. Min Range: -10.7568
Max Act: 9.8818. Min Act: -0.1700
Data Index: 2013495 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7568. Min Range: -10.7568
Max Act: 9.8818. Min Act: -0.1700
Data Index: 7000486 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19