Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1430 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0864. Min Range: -7.0864
Max Act: 7.0864. Min Act: -0.1700
Data Index: 7129923 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.8052. Min Act: -0.1700
Data Index: 313075 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.7739. Min Act: -0.1700
Data Index: 7047314 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.7427. Min Act: -0.1700
Data Index: 7697874 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.6802. Min Act: -0.1700
Data Index: 510587 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.6802. Min Act: -0.1700
Data Index: 663630 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.6177. Min Act: -0.1700
Data Index: 6733519 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.5864. Min Act: -0.1700
Data Index: 2240687 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.5864. Min Act: -0.1700
Data Index: 6028811 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.5864. Min Act: -0.1700
Data Index: 1720115 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.5552. Min Act: -0.1700
Data Index: 4115810 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.5239. Min Act: -0.1700
Data Index: 3127917 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.4927. Min Act: -0.1700
Data Index: 5580288 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.4927. Min Act: -0.1700
Data Index: 8244835 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.4614. Min Act: -0.1700
Data Index: 3387228 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.4614. Min Act: -0.1700
Data Index: 1861070 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.4614. Min Act: -0.1700
Data Index: 8792159 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.4302. Min Act: -0.1700
Data Index: 6336105 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.4302. Min Act: -0.1700
Data Index: 6526615 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0864. Min Range: -7.0864
Max Act: 6.4302. Min Act: -0.1700
Data Index: 6609051 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19