Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0808. Min Range: -7.0808
Max Act: 7.0495. Min Act: -0.1700
Data Index: 615587 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0808. Min Range: -7.0808
Max Act: 7.0808. Min Act: -0.1700
Data Index: 6512950 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.9245. Min Act: -0.1700
Data Index: 3304712 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.7370. Min Act: -0.1700
Data Index: 6709286 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.7370. Min Act: -0.1700
Data Index: 3526681 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.6745. Min Act: -0.1700
Data Index: 7091994 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.6433. Min Act: -0.1700
Data Index: 6085880 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.6433. Min Act: -0.1700
Data Index: 6621479 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.6433. Min Act: -0.1700
Data Index: 677174 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.6433. Min Act: -0.1700
Data Index: 10214 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.6120. Min Act: -0.1700
Data Index: 8054611 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.5495. Min Act: -0.1700
Data Index: 2693908 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.5183. Min Act: -0.1700
Data Index: 8308956 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.5183. Min Act: -0.1700
Data Index: 6640140 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.4870. Min Act: -0.1700
Data Index: 5489303 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.4870. Min Act: -0.1700
Data Index: 6237597 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.4870. Min Act: -0.1700
Data Index: 3106778 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.4870. Min Act: -0.1700
Data Index: 6621480 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.4870. Min Act: -0.1700
Data Index: 1555811 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0808. Min Range: -7.0808
Max Act: 6.3933. Min Act: -0.1700
Data Index: 2002598 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19