Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4146 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.3131. Min Act: -0.1700
Data Index: 4069240 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.3444. Min Act: -0.1700
Data Index: 373348 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.1874. Min Act: -0.1700
Data Index: 839465 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.2188. Min Act: -0.1700
Data Index: 30411 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.1874. Min Act: -0.1700
Data Index: 6107265 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.1559. Min Act: -0.1694
Data Index: 5297085 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.1559. Min Act: -0.1700
Data Index: 4996951 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.1559. Min Act: -0.1700
Data Index: 2692352 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.1244. Min Act: -0.1700
Data Index: 6327479 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.0613. Min Act: -0.1700
Data Index: 6597753 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.0929. Min Act: -0.1700
Data Index: 174913 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.0929. Min Act: -0.1700
Data Index: 508754 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.0929. Min Act: -0.1700
Data Index: 866759 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.0298. Min Act: -0.1700
Data Index: 8191326 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.0613. Min Act: -0.1700
Data Index: 5897054 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.0613. Min Act: -0.1700
Data Index: 4232082 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.0613. Min Act: -0.1700
Data Index: 5041656 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.0613. Min Act: -0.1699
Data Index: 3666168 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3444. Min Range: -3.3444
Max Act: 3.0140. Min Act: -0.1700
Data Index: 4082348 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3444. Min Range: -3.3444
Max Act: 2.9982. Min Act: -0.1700
Data Index: 7827741 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19