Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2110 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4908. Min Range: -8.4908
Max Act: 8.4908. Min Act: -0.1700
Data Index: 7658745 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4908. Min Range: -8.4908
Max Act: 8.4283. Min Act: -0.1700
Data Index: 3566327 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4908. Min Range: -8.4908
Max Act: 8.0533. Min Act: -0.1700
Data Index: 8041732 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.9595. Min Act: -0.1700
Data Index: 1376130 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.9908. Min Act: -0.1700
Data Index: 5946686 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.9908. Min Act: -0.1700
Data Index: 2167181 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.9595. Min Act: -0.1700
Data Index: 5128303 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.9595. Min Act: -0.1700
Data Index: 518534 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.9283. Min Act: -0.1700
Data Index: 4630919 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.9283. Min Act: -0.1700
Data Index: 5623020 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.9283. Min Act: -0.1700
Data Index: 518538 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.8970. Min Act: -0.1700
Data Index: 343201 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.8970. Min Act: -0.1700
Data Index: 7063603 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.8345. Min Act: -0.1700
Data Index: 4035628 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.8345. Min Act: -0.1700
Data Index: 1623322 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.8345. Min Act: -0.1700
Data Index: 2555057 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.7720. Min Act: -0.1700
Data Index: 3081246 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.7720. Min Act: -0.1700
Data Index: 3434636 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.7720. Min Act: -0.1700
Data Index: 518536 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4908. Min Range: -8.4908
Max Act: 7.8033. Min Act: -0.1700
Data Index: 4264118 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19