Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.5461. Min Act: -0.1700
Data Index: 3314626 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.2336. Min Act: -0.1700
Data Index: 5550576 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.2649. Min Act: -0.1700
Data Index: 5826975 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.2024. Min Act: -0.1700
Data Index: 4188345 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.1399. Min Act: -0.1700
Data Index: 1901113 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.1086. Min Act: -0.1700
Data Index: 4826550 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.1086. Min Act: -0.1700
Data Index: 7427467 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.1086. Min Act: -0.1700
Data Index: 5406687 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.1086. Min Act: -0.1700
Data Index: 7320121 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.1086. Min Act: -0.1700
Data Index: 732679 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.1086. Min Act: -0.1700
Data Index: 8187728 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.1086. Min Act: -0.1700
Data Index: 8029245 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.1086. Min Act: -0.1700
Data Index: 7474475 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.1086. Min Act: -0.1700
Data Index: 1232519 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.1086. Min Act: -0.1700
Data Index: 3835365 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.1086. Min Act: -0.1700
Data Index: 4576277 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.1086. Min Act: -0.1700
Data Index: 4508556 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.0461. Min Act: -0.1700
Data Index: 8397354 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.0461. Min Act: -0.1700
Data Index: 7832385 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5461. Min Range: -4.5461
Max Act: 4.0773. Min Act: -0.1700
Data Index: 503517 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19