Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 644 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0310. Min Range: -7.0310
Max Act: 7.0310. Min Act: -0.1700
Data Index: 4454599 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.8122. Min Act: -0.1700
Data Index: 5522549 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.5935. Min Act: -0.1700
Data Index: 434128 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.5622. Min Act: -0.1700
Data Index: 3954368 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.5310. Min Act: -0.1700
Data Index: 7778095 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.4997. Min Act: -0.1700
Data Index: 1405792 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.4685. Min Act: -0.1700
Data Index: 8178444 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.4060. Min Act: -0.1700
Data Index: 8083154 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.4060. Min Act: -0.1700
Data Index: 7998810 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.4060. Min Act: -0.1700
Data Index: 4550056 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.3747. Min Act: -0.1700
Data Index: 7874890 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.3435. Min Act: -0.1700
Data Index: 5732655 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.4060. Min Act: -0.1700
Data Index: 165149 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.3435. Min Act: -0.1700
Data Index: 2068985 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.3747. Min Act: -0.1700
Data Index: 7800538 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.3435. Min Act: -0.1700
Data Index: 4471515 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.3122. Min Act: -0.1700
Data Index: 5371910 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.3122. Min Act: -0.1700
Data Index: 569618 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.3122. Min Act: -0.1700
Data Index: 7069746 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0310. Min Range: -7.0310
Max Act: 6.2810. Min Act: -0.1700
Data Index: 1715333 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19