Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9484. Min Range: -9.9484
Max Act: 9.9484. Min Act: -0.1700
Data Index: 3636438 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.9484. Min Act: -0.1700
Data Index: 1257388 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.7609. Min Act: -0.1700
Data Index: 3382524 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.4484. Min Act: -0.1700
Data Index: 4589058 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.4484. Min Act: -0.1700
Data Index: 7613772 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.3859. Min Act: -0.1700
Data Index: 6214527 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.4172. Min Act: -0.1700
Data Index: 7122920 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.4172. Min Act: -0.1700
Data Index: 1023991 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.3859. Min Act: -0.1700
Data Index: 609216 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.3859. Min Act: -0.1700
Data Index: 930531 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.3859. Min Act: -0.1700
Data Index: 5702135 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.3859. Min Act: -0.1700
Data Index: 8379257 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.3547. Min Act: -0.1700
Data Index: 4445488 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.2609. Min Act: -0.1700
Data Index: 1056944 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.2922. Min Act: -0.1700
Data Index: 1795972 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.1984. Min Act: -0.1700
Data Index: 6932355 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.1672. Min Act: -0.1700
Data Index: 538216 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.0734. Min Act: -0.1700
Data Index: 8173054 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.1047. Min Act: -0.1700
Data Index: 3867543 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9484. Min Range: -9.9484
Max Act: 8.1047. Min Act: -0.1700
Data Index: 2295235 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19