Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3167 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.5327. Min Act: -0.1567
Data Index: 408945 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.5014. Min Act: -0.1699
Data Index: 3819362 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.4702. Min Act: -0.1567
Data Index: 379317 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.4389. Min Act: -0.1600
Data Index: 295727 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.3764. Min Act: -0.1700
Data Index: 3209030 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.3764. Min Act: -0.1700
Data Index: 8144320 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.3764. Min Act: -0.1567
Data Index: 5642858 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.3764. Min Act: -0.1617
Data Index: 1918178 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.3764. Min Act: -0.1649
Data Index: 1458853 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.3764. Min Act: -0.1567
Data Index: 5460948 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.3139. Min Act: -0.1700
Data Index: 7226704 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.3139. Min Act: -0.1678
Data Index: 2811585 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.3452. Min Act: -0.1698
Data Index: 5746697 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.3139. Min Act: -0.1567
Data Index: 6719295 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.3139. Min Act: -0.1567
Data Index: 1339873 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.2827. Min Act: -0.1692
Data Index: 6954609 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.2827. Min Act: -0.1697
Data Index: 4840449 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.2514. Min Act: -0.1567
Data Index: 6829738 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.2202. Min Act: -0.1653
Data Index: 289266 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5327. Min Range: -4.5327
Max Act: 4.2514. Min Act: -0.1567
Data Index: 4064058 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19